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

Beyond the readOnly and openWorld annotations, the description discloses the provenance model (recorded by a person, replayed and verified), the fields returned (cid, risk flags, approval steps, run counts, how_to_run), and the meaning of an empty result. This is unusually rich behavioral context for a discovery tool.

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 front-loaded with the purpose and concrete examples, then systematically covers return values and next steps. It is dense but each sentence carries useful information; minor tightening could improve readability.

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 no output schema, the description fully explains the shape of the result, including site_kind, parameters, risk flags, approval steps, and verification counts. It also covers the empty-result case and points to the correct next tool, leaving no major gap for invocation.

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 query and limit parameters are already documented in the schema. The description reinforces that query is a plain-language task, but adds no syntax, format, or limit semantics beyond what the schema provides.

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 uses a specific verb and resource: 'Find a verified browser skill,' and gives concrete task examples such as filling a form or exporting a report. It clearly distinguishes itself from siblings like get_skill and try_skill by describing the search-and-discovery role.

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 explicitly says to call it 'before operating a site step by step' and explains that an empty result means no skill exists yet. It also names the alternative path: this endpoint does not run skills, but allowlisted skills can be tried with try_skill.

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