agent_review_loop

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly describes the multi-step pipeline (Codex implements -> Evidence Gate validates -> Claude reviews -> auto-revision) and the auto-revision limit of 2. This gives the agent a good understanding of what the tool does and its boundaries, though it does not discuss side effects or what gets modified.

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, concise sentence that front-loads the key action ('Execute full autonomous development loop') and then lists the sequential steps. Every element earns its place, no 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?

Given the tool's complexity (8 parameters, multi-step process, no output schema), the description is reasonably complete. It explains the loop stages and constraints (max 2 revisions). However, it omits details like what 'Evidence Gate validates' entails or what the output/return value looks like, which would be helpful for an agent to determine success or failure.

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%, so each parameter has a description in the schema. The tool description itself does not add parameter-level detail, but given full coverage, a baseline of 3 is appropriate. An extra point is earned because the description effectively frames the purpose of the 'prompt' and 'maxRevisions' parameters in the context of the loop, adding semantic meaning beyond the schema.

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 uses specific verbs ('executes', 'validates', 'reviews') and clearly identifies the resource (a full development loop with multiple stages). It distinguishes itself from sibling tools like 'agent_send' or 'agent_evidence_check' by describing a multi-step autonomous process, not a single action.

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 context (autonomous development with revisions) and mentions a max revision limit, but does not explicitly say when to use this tool versus alternatives like 'agent_send' or 'agent_evidence_check'. There is no guidance on prerequisites or when not to use it.

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