review_run

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

No annotations are provided, so the description must carry the full burden. It mentions 'review' and 'create a state proposal' but does not disclose side effects, required permissions, or what 'review' entails (e.g., validation, modifications). For a tool that likely creates or modifies state, this is insufficient.

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 single, front-loaded sentence with no wasted words. It is concise, though it sacrifices detail.

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?

Given the absence of output schema and annotations, the description is too minimal. It does not explain what a 'state proposal' is, how it relates to sibling tools, or what the agent should expect after invocation. The tool's role in a pipeline is implied but not clear.

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 100% with clear parameter descriptions in the schema. The description adds no extra meaning beyond the schema, so a baseline of 3 is appropriate.

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 verb 'review' and the resource 'recorded draft', and specifies the output 'state proposal'. It distinguishes from siblings like inspect_run (inspection) and approve_run (approval) by indicating a preparatory step for human approval. However, it could be more explicit about what a 'state proposal' means.

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 description implies usage after build_context (as it uses run_id) and before human approval (approve_run). However, it gives no explicit when-to-use or when-not-to-use guidance, nor mentions alternatives like inspect_run or validate_project.

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