finish_review

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

With no annotations, the description carries the full burden and does well: it discloses side effects (sends, checks, scores, keeps, writes report.md), the retry behavior, and the return values (AI tell index and link). It could add more about failure modes, but it is already substantive.

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 description is a bit sentence-heavy but every sentence adds operational value: what to send, when to call, how to handle problems, and what is returned. It is slightly dense but well organized and front-loaded with the core action.

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 zero-parameter tool with no output schema, the description covers the full workflow: input file, destination, expected processing, retry guidance, and return values. Nothing essential is missing for an agent to invoke it correctly.

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?

The tool has zero parameters, so the baseline is 4. The description correctly avoids inventing parameter details and instead explains the data flow, which is more relevant here.

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 clearly states the specific action: sending report.json to Phyll's engine, which checks, scores, keeps it with a link, and writes report.md. It also distinguishes this from the workflow by explicitly saying 'Call it last,' which separates it from siblings like start_review.

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?

Provides explicit usage context: 'Call it last' and describes the retry loop when the engine returns a list of problems. It does not name alternatives or exclusions, but for a zero-parameter finalization tool, the guidance is clear and sufficient.

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