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

Annotations already cover read-only/idempotent/non-destructive, so the description usefully adds what they can't: bounded corpus, curated records, coverage statement and retrieval timestamps in the response, plus the important caveat that a changed source body does not establish a policy change. It doesn't mention result limits, ranking, or pagination, which would be the next layer of value.

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?

Three sentences, front-loaded with the identity and scope caveat before parameter routing. Dense but every sentence carries information; only the phrase 'retrieval or changed source body does not establish a policy change' is slightly convoluted.

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 7-parameter search tool with no annotations gaps on safety, no output schema, and zero schema coverage, the description covers scope and parameter roles but leaves the agent guessing about result shape, ordering, limits, and valid facet values. Adequate, not complete.

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%, so the description must compensate, and it does partially by mapping each of the seven parameters to its role (q as substring over title/summary/topic; since vs changed_since; exact topic vs substring). However, it gives no formats (ISO date examples, allowed jurisdiction or status values), and with no enums an agent still cannot know valid inputs.

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 and resource ('Search ... frontier-AI policy registry') and immediately sets scope with 'bounded, source-labelled'. It also explicitly disclaims being a comprehensive legislative database, which distinguishes it from siblings like search_legislation. It doesn't name a sibling directly, so 4 rather than 5.

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 concrete routing guidance: use structured fields (jurisdiction, instrument_type, status, topic) for facets and `q` for title/summary/topic substring. It also frames coverage limits so an agent knows when this tool is insufficient. It stops short of naming alternatives like search_legislation or get_jurisdiction_coverage for out-of-scope needs.

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