search_used_parts

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

Beyond the annotations it explains the inspection budget (one search plus up to 5 card reads, default 3), the filter semantics (only structured Б/у passes, new/unknown excluded and counted, broken/repair retained with text signals), and result instability across calls. readOnlyHint/destructiveHint are consistent with this; 'results can shift between calls' sits in mild tension with idempotentHint but does not contradict it since no environment state is modified.

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?

Four short sentences, front-loaded with the purpose, then the cost model, the filter rule, and the scope limits. No filler, and each sentence carries a distinct operational fact.

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?

The core mechanics of a 10-parameter, no-output-schema tool are covered, but the definition is silent on the majority of filter parameters and on what a result record contains beyond condition text. An agent can call it correctly on query/inspect_limit/pagination but will underuse the filtering surface.

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 description coverage is 0% across 10 parameters, so the description must carry the load; it does explain the non-obvious dual pagination (offset within a page, then page) and inspect_limit's default/max. It says nothing about city, sort, price_min/price_max, local_only, or seller_type, leaving most filtering parameters to be guessed from the schema alone.

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 concrete verb and resource ('Find used PC parts') plus the distinguishing mechanism ('checking the actual condition in full listing cards'), which separates it from a plain listing search. It never names the sibling search_listings explicitly, so the boundary is implied rather than stated.

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 real usage boundaries — 'bounded scan of ONE page, not exhaustive or globally cheapest' and continuation instructions. However, those are pagination rules rather than a when-to-use-this-vs-search_listings/get_listing/compare_listings rationale, so an agent still has to infer tool selection.

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