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

Beyond the annotations (destructiveHint=true, openWorldHint=false), the description explains that approval applies the change under that change's own permission and that a refusal returns as FAILED with the reason rather than failing silently. It does not say whether dismissal is reversible or describe any validation of the edited payload, but it adds meaningful behavioral context that the annotations alone do not convey.

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?

Three sentences, front-loaded with the action and decision modes, followed by behavioral consequences and then the usage constraint. Every sentence carries distinct information with no repetition.

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?

For a destructive mutation with an output schema present, the description is behaviorally strong but does not cover the low-coverage parameters (edited, reason). It tells the agent when to call and what refusal looks like, yet leaves gaps an agent would need to fill before constructing the edited payload or reason.

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 only 25%, and the description does not explain the 'edited' object, the 'reason' string, or the shape of 'proposalId' beyond what the schema already states. The three decision modes loosely map to the enum values, but the remaining parameters are left undocumented in both schema and description.

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 names a specific verb and resource: it 'Approves, approves with an edit, or dismisses a proposal,' covering all three decision modes. It does not explicitly distinguish itself from sibling tools such as fundraising_propose_change or fundraising_get_list_proposals, leaving a small ambiguity about create-versus-decide workflows.

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?

It gives a clear, explicit precondition: 'Only call this when the member has said, in their own words, that they approve or dismiss this specific proposal.' This tells the agent when to act and implies when not to, but it names no alternative tool or fallback for cases where the member has not yet decided.

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