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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds substantial behavioral context beyond that: the all-words-must-match constraint, the word-dropping retry mechanism, the 10-result cap, and the exact return shape (type, Markdown URL, short description). The retry behavior is especially valuable because it changes how an agent should interpret sparse results.

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?

The description is five sentences and every one earns its place: purpose, retry behavior, query strategy, return format, and sibling routing. It is front-loaded with the core purpose. It is slightly dense in the middle (retry explanation could be tightened), but nothing is wasted.

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?

There is no output schema, so the description carries the burden of explaining return values — it does ('up to 10 ranked pages with their type, Markdown URL, and a short description'). Combined with annotations covering safety and the single fully-documented parameter, an agent has everything needed to invoke this tool correctly.

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 coverage is 100% so the baseline is 3, and the description adds value on top: it teaches query formulation strategy ('2-3 core topic words; add words only to narrow') and explains the success/failure semantics of the query in a way the schema's static description cannot. This pushes it above baseline.

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 — 'Keyword search over Particular Platform documentation' — and distinguishes itself from the only sibling, read_doc, by defining the division of labor: search returns URLs, read_doc consumes them. An agent can tell these two tools apart without opening either 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?

Provides concrete search strategy — 'Start with 2-3 core topic words; add words only to narrow' — and explains the automatic retry-with-fewer-words fallback so an agent knows what to do when results are empty. It names the alternative (read_doc) as the follow-up for returned URLs, though it doesn't state an explicit when-not-to-use exclusion for the search tool itself.

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