Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial context beyond annotations: it discloses the underlying vision/LLM 'autopilot inference', the FAA registry lookup behavior triggered by anchoring, the tiered auth requirement, per-field source reporting, and a ready-to-POST report_input. The readOnlyHint=false is consistent with a tool that must be gated behind PRO/Enterprise and produces downstream artifacts; nothing is contradicted.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense paragraph with the core action front-loaded and no filler sentences. Slightly packed with clauses, but every element (specs, sources, storage anchor, impute, auth) earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter inference tool with an output schema, it covers what an agent needs: inputs accepted, anchoring behavior, gap-filling option, auth gate, and a preview of the return shape. Nothing material is left unexplained.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema carries the baseline (3). The description still adds meaning: it explains that registration/make_model_id pull make/model and year from the FAA registry, that images may be a listing's own photos or data: URLs, and how impute relates to the imputation model — more than the terse schema strings convey.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Extract') and resource ('aircraft specs') and enumerates exactly what is extracted (AFTT, SMOH for engine 1/2, prop time, year, quality ratings, avionics). The scope — observable page content (text and/or image URLs) — cleanly separates it from the sibling impute_aircraft_specs, which is referenced only as a gap-filling model.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear activation context: extract from visible text or image URLs, anchor with registration/make_model_id, and set impute=true to fill gaps. Prerequisites (Windsock PRO or Enterprise) are stated outright. It stops short of an explicit 'use this instead of X' routing statement, but the boundary with the imputation model is implied clearly enough.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.