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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: conjunctive matching (all query terms must match), ranked excerpt/section output with canonical URLs, and confinement to public content only. No rate limits or failure behavior, but solid.

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 tight sentences, scope first, output shape second, sibling boundary third. The final sentence about 'live memories and experimental manifests' is slightly opaque but earns its place as a disambiguator.

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?

No output schema exists, and the description does partially describe returns (ranked excerpts, sections, canonical URLs). However, with 0% schema coverage on four parameters and an unenumerated kind filter, the definition leaves materially important selection controls 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 description coverage is 0%, so all four parameters (query, kind, limit, offset) are undocumented in structured fields. The description never explains the kind enum values (memo/product/page/guide), the 1-20 limit bound, or offset pagination, and only loosely gestures at content categories via 'published pages' and 'references/interfaces'.

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) and a clearly bounded resource (the complete public site snapshot: published pages plus explicitly public references/interfaces). It also distinguishes itself from memory-oriented siblings by noting that memories use separate contracts. The phrase 'same ... as browser search' is a bit referential but still conveys scope.

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?

Implies when to use it (searching public site content) and explicitly excludes live memories and experimental manifests, pointing to their separate contracts. It does not name specific sibling tools like search_memories, so the routing requires the agent to map 'separate public contracts' onto those siblings.

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