catalog_search

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

No annotations are provided, so the description carries the full burden — and it does: 'Offline, deterministic, zero network' declares the side-effect profile, and it proactively warns that availability is 'a curated snapshot of a MARKET... not physics' and to 'read `not_covered` before concluding from an empty result that a part does not exist.' That is exactly the caveat an agent would otherwise get wrong.

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?

Front-loaded with the essential distinction and structured as filter list + return-shape list, so it scans well. It is somewhat long and includes a rhetorical 'somebody can build' clause, but nearly every sentence carries actionable content.

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?

With no output schema, the description fully enumerates the return envelope ({ok, count, truncated, items, standards, fidelity, captured, market, not_covered}) and the item shape, and it flags the truncation and market-fidelity semantics. An agent has everything needed to call it and interpret results.

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% and there are 10 parameters, so the description must compensate — it documents every filter with example values and accepted vocabularies (family enum of 9 names, 'ISO 4762' or 'DIN 912' for standard, min_length/max_length window semantics, limit default 50). This adds meaning the bare anyOf/null schema does not.

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+resource ('Browse the off-the-shelf catalog') and then draws the exact boundary against adjacent tool families: 'The dimensional corpora (threads/bearings/stock) tell you what a part measures. This one tells you whether it is a thing you can buy.' An agent can distinguish it from catalog_nearest, list_thread_options and the geometry builders without opening a schema.

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 explicit when ('Call it while designing, before you commit geometry to a number') and an explicit contrast with the tools it resembles, plus the consequence of skipping it ('the difference between a design somebody can build and one that needs a special'). The 'run this before you pick catalog_nearest/catalog_check' workflow is inferable from the stated sequencing.

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