Decide Proposal

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

With no annotations, the description carries the full behavioral burden and does so thoroughly. It discloses mutation side effects, authorization requirements, HTTP 403 refusal behavior, creation of a decision_request, and the escalation_id. It even warns that this is a judgment call, which is useful context for the agent.

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 compact and front-loaded with the core action, followed by policy, mutation, and failure handling. Every sentence adds information, and there is no filler or repetition of schema details.

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?

The definition covers purpose, permission precondition, side effects, error behavior, escalation semantics, and follow-up actions. Since an output schema exists, not detailing the return value is acceptable. The agent has enough context to invoke this tool correctly and handle refusals gracefully.

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 80%, so the schema already documents most parameters. The description adds high-level meaning to decision and proposal_id through context like "Accept or reject a proposal," but it does not add details beyond the schema for note, model_id, or server_version. The 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 opens with a specific verb and resource: "Accept or reject a proposal." It further clarifies the effect with "Mutating: closes the proposal and applies an accepted change," which clearly distinguishes this mutation tool from read-only proposal and work-order siblings.

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 gives an explicit precondition: "Call this only when the workspace's delegation policy names this decision for this agent at the proposal's tier." It also tells the agent exactly what to do on refusal: report the escalation_id, poll list_proposals, and continue other work, including "Do not retry a refusal."

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