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

Annotations cover destructive/idempotent/readOnly, but the description adds the effects the annotations cannot express: irreversibility, name and amount appearing on page and stream overlays, counting toward totals and the active goal, goal auto-completion and removal from the page, and that nothing is sent to the supporter. These are precisely the consequences an agent must weigh before a one-way action.

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-loads the action and its precondition, then layers consequences, parameter behavior, and the safety warning in short, information-dense sentences. Six sentences and every one carries decision-relevant content; no filler or restated boilerplate.

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, one-way approval with an output schema already present, the description supplies the missing pieces: prerequisites, irreversibility, downstream page/goal effects, reply and hidden semantics, and the consent constraint. Nothing material is left for the agent to guess.

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 67% and the schema already documents reply (280 chars, replaces existing, word-filter refusal) and hidden (message/voice private, name/amount still shown) in nearly the same words, so the description largely duplicates structured data. It adds no prose for id and only marginally extends the parameters by tying them to visible outcomes.

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 ("Approve one supporter") and instantly scopes it as the single-support path versus the sibling bulk_approve_supports. The description also names the precondition that makes it distinct from a generic approval endpoint (creator must have verified payment).

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?

Gives an explicit when-to-use rule ("after the creator has found the payment in their own bank app") and a hard when-not rule ("never approve without being asked to for that specific supporter"), plus the rationale that only the creator can know the money arrived. That is exactly the guidance an agent needs before calling a destructive approval.

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