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

Annotations already declare readOnlyHint=true and openWorldHint=false, yet the description still adds real context: calls count toward account usage and appear in the activity log, semantic matching only applies when enabled for the account, and results include snippets and original URLs. These are operational traits an agent could not infer from structured fields.

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?

Five short sentences, zero filler, front-loaded with what the tool does and the query-omission behavior, then scope limits, return shape, and side effects. Every sentence carries information an agent needs.

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 an eight-parameter, no-output-schema search tool, the definition covers scope, exclusions, return shape, pagination, and usage accounting. Remaining gaps are result ordering and filter-combination semantics, which matter for constructing precise queries but are secondary.

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 75%, so the baseline is high, but the description still contributes meaning: omitting query lists newest imports, the newsletter platform case is explained as forwarded mail to the user's Pro address, and limit/offset are characterized as pagination. It does not say whether filters combine conjunctively or how results are ordered.

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 with scope: searching posts already imported into the authenticated user's library, with keyword plus optional semantic matching. It carves out what it is not (live web search, platform sync), but never names the sibling recent_saves even though omitting query reproduces that tool's behavior.

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 explicit use cases (find saved content by topic, author, platform, or collection) and explicit exclusions (no live web, no platform sync). Cross-references list_collections via the collection_id note. Missing only the direct routing comparison against recent_saves and get_collection_saves.

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