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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: matching is case-insensitive, results are ordered newest key date first, and the result window defaults to 20 with a hard cap of 50.

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?

Two sentences with the matching semantics front-loaded and no filler. The only wasted effort is restating the 20 default and 50 maximum that the limit schema already enforces.

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?

An output schema exists so return shape need not be explained, and the description covers matching rules, ordering and result limits. What is missing is minor: no mention of what happens on zero matches or whether cursor-based paging beyond limit is possible.

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?

The query parameter carries no schema description, and the description compensates by explaining that it is matched case-insensitively against summary, vendor and signatures. Limit and vendor are already documented in the schema, and the description only repeats the 20/50 bounds rather than adding to them.

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 (search) plus resource (apiwatch's feed of reviewed vendor changes) and exactly what text is matched against: summary, vendor and signatures. It also distinguishes itself from id-based lookup by saying it is for when you know a name 'but not the exact id'.

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 a clear triggering condition ('when you know a product or feature name but not the exact id'), which implicitly separates it from get_record. It does not name get_record as the alternative outright, so the exclusion is inferable rather than explicit.

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