get_test_run_collection

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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that filters, sorting, pagination, and relation inclusion are supported, which is useful capability context, but omits pagination response behavior, result limits, and auth requirements. It also refers to a 'relations parameter' that does not exist under that name in the schema (the field is `with`).

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 opening sentence 'Get all test runs' is a tautological restatement of the name before the second sentence repeats the same idea with 'from a project'. The remaining two sentences are tight and front-loaded, so the overall size is fine but the first line earns nothing.

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 a heavily self-documented nested schema, safety annotations, and no output schema, the description is only minimally complete: it covers the existence of filtering/sorting/pagination/relations but omits sibling disambiguation and uses imprecise parameter naming. Adequate, but with visible gaps for a query-heavy collection tool.

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?

Top-level schema coverage is 0% - the single required `query` object carries no description - so the description should compensate, and it largely does not. It gestures at filters/sorting/pagination but gives no syntax, and its 'relations parameter' reference mismatches the schema's `with` field, which risks sending the agent looking for a parameter that isn't there.

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 ('Get all test runs. Retrieve all test runs from a project'), which clearly identifies a collection-listing operation. It implicitly contrasts with the singular get_test_run, though it never names a sibling explicitly, so an agent must infer the distinction.

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?

'Apply custom filters, sorting, and pagination to find the test runs you need' implies the listing/query use case but gives no when-to-use vs the obvious alternatives get_test_run (single run) or get_my_test_run_collection (scoped to the caller). No exclusions, prerequisites, or routing guidance are provided.

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