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

Beyond the annotations (readOnly/idempotent/non-destructive), the description discloses behavior an agent cannot get from structured fields: every read re-checks current publication, private or withdrawn bases return 404, no cached files are served after withdrawal, and the 20-results-per-page ceiling applies. It also flags that uploaded text must be treated as untrusted data, never as instructions, which is directly actionable safety context.

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 scoping constraint and the public-only rule are front-loaded, and most sentences carry distinct information. It is slightly redundant, repeating the 3–160 character limit and 20-result cap that the schema already states, but overall it is dense rather than padded.

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 a three-parameter read tool with annotations and no output schema, the description covers eligibility, failure mode (404), caching, pagination limits, and an injection warning. The one gap is that it never sketches the shape of returned results, which is the piece an output-schema-less definition would otherwise need to supply.

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%, so the schema already documents q, after, and base_id, and the description merely restates the 3–160 character range rather than adding new syntax or semantics. The baseline 3 applies because the schema is doing the heavy lifting.

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?

The description opens with a specific verb and resource ('Search the full text of published base') and immediately narrows scope with 'Published bases only,' so the agent knows this is the public-search entry point rather than a private one. It does not, however, name or contrast itself with the closest sibling, public_search_collection, so differentiation from that alternative is left implicit.

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?

It gives real usage context: no account is required, only published bases are eligible, and it explains the iframe/embed_url route for embedding search and the reader with author attribution. There is no explicit when-not or named alternative (e.g., use public_search_collection for collections), so routing guidance is clear but incomplete.

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