report_results

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

With no annotations, the description carries the full burden and does disclose mutations: plan custom_fields are written ('other existing values are preserved' is in schema, not description), omitted assigned executions can be marked skipped, and 'only after all supplied results succeed' signals partial-failure ordering. It also rules out adjacent behaviors ('no report-file parsing, auto-create or builds') and mentions MCP provenance recording. Remaining gaps are permissions/auth and re-report overwrite semantics.

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 tight sentences with the core action front-loaded and constraints packed into semicolon clauses; little waste. The run-on 'Defaults to the latest run; configuration_id selects matrix executions' slightly compresses two unrelated facts into one line, but nothing is filler.

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 6-parameter mutation tool with no annotations and no output schema, the description covers scope, defaults, and skip semantics reasonably well. It stops short of telling the agent what a call returns (counts, per-result status, error shape) and whether re-reporting the same case overwrites prior results, both of which matter given there is no output schema to fall back 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 coverage is 67%, so the schema already documents most parameters (run_id default, skip_missing, custom_fields preservation, configuration_id). The description mostly restates those and adds only the matrix-execution framing for configuration_id, which is confusingly stated as if top-level when it is actually nested in each result item.

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 ('Report a structured list of results') scoped to 'the caller's assigned executions in a plan', which implicitly distinguishes it from the singular sibling report_test_case_result. It does not name that sibling explicitly, so the differentiation rests on the agent noticing 'list' vs. one-case reporting.

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?

The scope ('caller's assigned executions') and defaults ('Defaults to the latest run; configuration_id selects matrix executions') give useful context for when this applies. However, it never states the exclusion the siblings demand: when to call this batch tool versus report_test_case_result, or what preconditions (plan assignment) must hold before calling.

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