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

Goes well beyond the readOnly/idempotent annotations by disclosing what the search actually covers (owned current files vs. published files in other bases), that publication is re-validated on every public read, that private or withdrawn collections return 404, and that responses are private/no-store. These are non-obvious 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?

The purpose is correctly front-loaded in the first sentence, but the bulk of the text is publication/permission semantics with some redundancy ('Publication includes only references to currently public bases' followed by 'Every public read checks base publication again'). Useful but not tight; two of the six sentences could be merged.

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 bears responsibility for describing returns, and it does not — nothing about result shape, pagination beyond the cursor hint in the schema, or whether snippets are included. The permission, error, and caching behavior is well covered, which offsets the missing return-value detail but leaves a real gap for a search endpoint.

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 100%: q's length and FULLTEXT semantics, after's cursor warning, and collection_id's 64-character format are all documented in the schema itself. The description adds no parameter-level detail (e.g., how multiple terms are matched or how q interacts with collection scope), so baseline 3 is appropriate.

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: 'Search documents across bases in your collection.' It also clarifies the underlying model ('Collections store references, not copied content'), which helps an agent distinguish it from search_base. It never names alternative siblings (public_search_collection, team_search_collection) explicitly, so sibling differentiation is implied rather than stated.

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?

Usage context is implied through scope statements ('Owner search reads current files in owned bases and published files in other bases'), which tells the agent what this tool will and won't surface. However, there is no explicit when-to-use framing, no mention of when to prefer search_base or the public/team variants, and no prerequisite guidance beyond the 404 note.

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