create_test_result

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

No annotations exist, so the description carries the full burden — and it does: version-specific auto-add behavior, silent discard of out-of-range scriptResults indices, status never being derived from step statuses, 400/404 and empty-bodied 500 responses, and the warning that a 500 may still have written the execution and duplicated an item. These are exactly the failure modes an agent must know before retrying.

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?

Front-loaded correctly — what it does, the sibling alternative, then hazards. But it runs to roughly 400 words with hedged speculation and low-value specifics ('it landed second of three and second of four', 'its cause is undetermined') that a caller cannot act on; a tighter version would preserve the actionable warnings and drop the field-report narrative.

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 17-parameter mutation tool with nested scriptResults, no annotations and no output schema, the description closes every gap: it documents the return value ({ id }), the selector-vs-body distinction, and the recovery path (re-read with get_test_run_results rather than retry). Nothing an agent needs to call it safely is missing.

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 already 100%, so the baseline is 3. The description still adds real meaning beyond the schema: the status/scriptResults coupling rule, the fact that omitted fields keep project defaults, that selectors only select and never set (so `environment` must be passed separately if the result should carry it), and that matchUserKey targets executedBy, not assignedTo.

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+resource ('Record a NEW execution of a run item') and even names the endpoint, then immediately distinguishes itself from update_last_test_result, the sibling it is most likely to be confused with. An agent can route correctly without opening the schema.

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?

Explicit when-to-use vs. when-not: 'to amend the newest execution instead, use update_last_test_result', plus conditional guidance to pass matchEnvironment/matchUserKey whenever a case appears more than once, and to pass `status` in the same call as scriptResults. Alternatives and preconditions are named, not implied.

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