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

Beyond the destructive/non-idempotent/openWorld annotations, it discloses that the write goes to GitHub as a commit or PR, is made 'on their behalf', is single-shot 'within 24 hours', and is refused once the change diverges from the preview. The expiry window and staleness guard are exactly the behavioral context annotations cannot express.

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 core action and constraints are front-loaded in the first sentence, and the timing and staleness rules follow immediately. The closing sentence 'For a change the person has seen and said yes to' largely repeats the title and the first sentence's 'the person saw in a preview', so it is slight padding.

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?

With an output schema present, return values need not be explained, and the description covers destination, consent requirement, expiry, and staleness. It stops short of describing what an agent should do when the 24-hour window has lapsed or the preview is stale (error surface), which matters for a destructive, non-idempotent call.

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% and both parameters are already documented, including that 'proposal' is the id send_change returned. The description only restates that provenance ('the proposal id that came with the preview') and says nothing about 'project' scope beyond the schema's own note.

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 and resource ('sends to GitHub, as a commit or a pull request'), the object acted on ('a change the person saw in a preview'), and the keying parameter ('the proposal id that came with the preview'). This clearly separates it from send_change, which produces the proposal, while confirm_send consumes it.

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 precondition is explicit and repeated: only 'a change the person has seen and said yes to' that is still 'as they saw it'. It does not explicitly name send_change as the alternative to use when no preview/consent exists, so the when-not side is only implied.

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