Search

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds what they cannot: results come back as snippets rather than full bodies, and coverage is limited to content the caller can access. It does not discuss ranking, empty-result behavior, or paging beyond the schema's limit, which keeps it short of a 5.

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 short sentences, organized as capability, return shape plus follow-up, then narrowing options, then the alternative. Every clause carries actionable information and the most important facts come first.

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 an output schema present, the description needn't explain result structure, and the schema covers parameter constraints and version prerequisites. The remaining agent-facing gaps — result format at a high level, access scoping, and sibling routing — are all answered.

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 all six parameters are already documented in the schema. The description's 'narrowed to titles, labels or pages you created' paraphrases title_only, labels, and created_by_me but adds no detail beyond them, and space_id and limit go unmentioned in prose — baseline 3 applies.

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 ('Full-text search over page titles and bodies') plus the access scope ('you can access'). It names the sibling it is not ('suggest' for partial-name/person lookup) and the follow-up tool ('get_page'), so an agent can place it precisely among the 60+ siblings.

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?

Explicit routing: use get_page to read a hit, use suggest when you only have part of a name or need a person. Also states the narrowing options, so an agent knows both when to pick this tool and how to scope the call.

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