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

Annotations already convey read-only/destructive/idempotence hints, and the description adds meaningful context: the CDP-authenticated pending reservation requirement, the one-time return of the capability, and the rule that secret-bearing input/output must not be logged. This does not contradict the annotations.

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 description is short and contains no filler, with the security instruction clearly stated. It is not perfectly front-loaded because it opens with the vague verb 'Manage' instead of leading with the revoke operation.

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 three-parameter tool with rich annotations and full schema coverage, the definition provides the required auth model, secret-handling rule, and operation scope. It does not describe return values or what happens to the capability after use, but the idempotent and non-destructive hints cover part of that 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 100%, so the schema already documents all three parameters. The root schema description adds the important 'Use capability OR accessToken plus sessionId' relationship, but the top-level description contributes no additional parameter-level meaning.

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 top-level description says only 'Manage same-wallet research autopay', which is a generic verb that could apply to enroll, status, or revoke. The revoke action is explicit only in the schema-level description ('Revokes this research session') and in the tool name/title, so the description itself does not clearly state the specific operation.

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 description provides a useful prerequisite ('Enrollment needs a CDP-authenticated pending reservation; capability is returned once') and the schema scopes the operation to 'this research session, not the global provider grant'. However, it never explicitly states when to use this tool versus sibling tools such as otto_muse_autopay_enroll, otto_muse_autopay_status, or otto_muse_autopay_prepare.

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