Whatic IC Datasheets

Shortlist IC part numbers by parametric spec constraints, ranked by how many constraints each part satisfies, then by headroom past those thresholds, and spread across device families. Each constraint is {canonical, op: gte|lte|eq|range, value, unit?}. Returns per-constraint pass/fail/unknown, plus `matched` (parts meeting EVERY constraint), `ranked` (all parts scored, partial matches included) and `returned` (parts in this response). `truncated` means some qualifying parts are not on this page. When `matched` is 0 every result is a partial match. `canonical` MUST be one of the exact (case-sensitive) names enumerated in this tool's inputSchema, also readable as the whatic://parametric/canonicals resource.

Read canonical extracted specs (min/typ/max, unit, conditions) for known IC part numbers from a pre-extracted parametric index — not from datasheet text. This is the cheapest and most precise source for numeric parameters where it has coverage. Optionally restrict to specific canonical parameter names. A part absent from `results` (with a "No specs found" warning) means no index coverage, not that the datasheet lacks the parameter — fall back to `lookup` for that part.

Relative price tier, stock posture, and library class for a set of IC part numbers (a ranking from a distributor snapshot, not a live quote).

Search the datasheet corpus; returns hit records (metadata + snippet, each with an opaque `ref`). Pass a ref list to `get_segments` for full content. If you already know the part number(s), prefer `lookup` — it fuses this search with `get_segments` in one call and groups full content per part. Use `search` when the part is unknown, or to triage snippets before pulling full content. For part-specific queries, pass scope='device:<MPN>' (e.g. scope='device:NE5532') to restrict hits to that part and avoid cross-part contamination.

One-shot spec/section retrieval: full content of the most relevant datasheet segments for one or more parts (fuses search+get_segments). Already groups results per part (via `parts`), so prefer `lookup` over `search` when you know the part(s).

Expand opaque `ref` tokens (from search/lookup) into full datasheet segment content.

Fetch datasheet figure images (PNG/JPEG) for opaque `ref` tokens obtained from search/lookup/get_segments. Returns each image plus its caption/description/page metadata. Only `type='image'` segments have image data; a ref that is not one comes back as an error record whose `available_images` lists the document's figures nearest that ref's page and section, closest first.