validate_aql

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

With no annotations, the description carries the burden and does reasonably well: it implies a non-mutating check ('a typo is caught before a real search'), explains the returned `count` as a preview of selection size, and discloses two defaults (project_id falls back to TESTOPS_PROJECT_ID, deleted=true includes removed cases). It never explicitly says the call performs no writes or has no side effects, which matters given the absent readOnlyHint.

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, front-loaded with purpose, then return contract, then parameter defaults. Nothing is padded and the sibling reference is placed where it does the most routing work.

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?

An output schema exists, so the description need not enumerate return fields; explaining only the meaning of `count` is the right level. All three parameters are covered despite zero schema coverage. The one gap is the unstated no-side-effects guarantee on a tool with no annotations to lean on.

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 0%, so the description must compensate, and it does for all three parameters: rql is flagged required with the AQL/RQL naming note, deleted is given real semantics ('counts removed cases too'), and project_id's fallback is explained. What is missing is any hint about AQL/RQL syntax or expression form, which matters for the primary parameter.

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 ('Check an AQL query') and immediately resolves the naming ambiguity ('the API calls it rql') that would otherwise confuse an agent reading the schema's `rql` parameter. It also positions the tool relative to a named sibling, search_test_cases, so it is not mistaken for the search itself.

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 is stated clearly via 'before running search_test_cases', which tells the agent this is a pre-flight check rather than a search. There is no explicit when-not or statement of what to do if validation fails, so it stops short of full routing guidance.

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