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

Annotations only supply readOnlyHint=false (a write). The description adds real behavioral context beyond that: the human is the approver, the request does not exist until approval occurs, and the payments:request scope is required. It does not disclose what happens on rejection, whether requests expire, or any rate limits.

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 short sentences, front-loaded with the action, then the role boundary, then the auth requirement. Every sentence carries distinct information and none is redundant with the title or schema.

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 mutation tool with no output schema and only a single annotation, the description covers purpose, actor model, and auth scope, but leaves all five parameters unexplained — notably dry_run, whose semantics materially change the call. Adequate but with a clear gap.

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 0% across five parameters, and the description explains none of them — amount, task_title, conversation_id, note, and dry_run are left entirely undocumented. The description does not compensate for the coverage gap, so an agent must guess at formats and the meaning of dry_run in particular.

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 ('Ask the human to approve a payment request in a conversation'), and clarifies the agent's role boundary versus the human's. It is clearly distinguishable from siblings like check_approvals or send_message, which are adjacent in the approval/payment domain.

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 clear context for use (payment requests in a conversation) and an explicit boundary ('You cannot approve or send money: the human decides'), which tells the agent this is a request-for-approval path rather than a settlement path. It does not name an alternative tool or state when *not* to use it, so it stops short of a 5.

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