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

Annotations already mark this destructive, open-world and non-idempotent, so the bar is lower. The description still adds real context: it executes exactly once, only within ten minutes of the preview, and records both the payload sent and the response on the project — behavior an agent could not infer from the annotations alone.

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?

Front-loaded with the action and its precondition, then the time limit, then the recording side effect — good ordering. The closing sentence duplicates the opening and earns little, keeping it from a 5.

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?

An output schema exists, so return values need not be described. The description covers the important operational traits (single execution, ten-minute window, recording on the project) and the schema covers all four parameters. Only the missing sibling routing keeps it from 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%, so the schema already explains project, proposal, leave_out_ask and leave_out_did. The description only reinforces the provenance of the proposal id ('that came with the preview') and says nothing about the leave_out flags or the project-vs-address fallback. 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?

States a specific verb and resource: runs an outside agent's tool that a person approved in a preview, keyed by proposal id. That is distinguishable from siblings like use_agent or agent_tools (which likely surface tools rather than execute an approved proposal). The trailing sentence 'For what the person has seen and said yes to' restates rather than sharpens, so it stops short of a 5.

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?

Usage is implied through the precondition (the person saw the preview and said yes) and the hard constraint (runs once, within ten minutes of the preview). However, no sibling is named as an alternative — nothing tells the agent to call confirm_hand_out/confirm_send or use_agent instead in a different situation.

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