get_review_feedback

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

With no annotations, the description carries the full burden and mostly delivers: it declares 'Read-only' (substituting for readOnlyHint), describes two behavioral modes (pre- vs post-submission), and flags that refresh_analysis discards the data. It stops short of covering error cases, permissions, or response shape when feedback does not yet exist.

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 short sentences, front-loaded with the primary purpose, then the pre-submission variant, then the ordering hazard. Every sentence carries distinct information with no repetition.

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 and no annotations, so the description is the only source of return-value and safety information — and it covers both the post-submission payload and the pre-submission progress state adequately. A brief note on what happens with an invalid or unknown analysis_id would make it fully complete.

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 100%, and the single analysis_id parameter is documented in the schema as coming from create_analysis or list_analyses. The description adds no extra meaning about the identifier, so the baseline 3 applies.

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?

Names a specific verb (read) and resource (the reviewer's feedback) and enumerates the payload: decision, selected findings and notes, and the prompt to act on. It also distinguishes itself from get_analysis by describing state-dependent content, and explicitly names refresh_analysis as the contrasting sibling.

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?

Gives an explicit when: after submission you get the final feedback, before submission you get progress. It also gives a hard ordering rule — 'Always read the feedback before calling refresh_analysis, which discards it' — naming the alternative and the consequence of sequencing incorrectly.

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