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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavior beyond them by enumerating the exact pass/fail conditions (missing email, unexpected email, failed check, failing note, failed: true), which tells the agent what outcome to expect. It does not clarify whether a failing run errors out or simply returns a failing report, leaving one behavioral ambiguity.

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 sentences, front-loaded with the action and output format; the middle sentence packs the failure conditions efficiently. 'Show the person the report' is a little colloquial but earns its place as an output-handling instruction.

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?

There is no output schema, so the description carries the return-value burden and does so by specifying Markdown format and intended destination. Pass/fail logic is covered. The one missing piece is the failure mode (does the call raise or return a failing report), which matters for a non-read-only 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?

Schema coverage is 50%: run_id is documented in the schema but 'failed' is not. The description compensates by explaining the failed flag ('failed: true says your test failed'), giving the agent the meaning of the undocumented parameter. The run_id semantics ('what this call sees is added to its report') come from the schema, not the description.

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 ('Finishes a run') plus the return artifact ('report in Markdown'), which is enough to distinguish it from start_run, add_run_note and the check_* siblings by the 'run' concept. It stops short of explicitly naming which sibling to use instead, so it is clear but not fully differentiated.

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?

'ready for a pull request comment or a reply' and 'Show the person the report' give downstream usage context, implying this is the closing step of a run. There is no explicit when-to-call/when-not-to-call statement and no named alternative, so usage is only implied.

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