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

Beyond the readOnly/idempotent/destructive annotations, the description adds two meaningful behaviors: enrollment requires a CDP-authenticated pending reservation and the capability credential is returned only once. The explicit warning that secret-bearing input/output must not be logged is useful security context. The word 'Manage' is slightly in tension with readOnlyHint, but it is not a direct contradiction.

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 terse sentences with no repetition; the secret-handling warning and enrollment prerequisite each add useful information. It loses a point because the first sentence uses 'Manage' instead of a precise operation, which forces the reader to infer meaning.

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 tool with six optional parameters and no output schema, the description is not complete enough: it doesn't describe what a caller receives back, what a status operation means, how operationId is used, or which sibling prepare/enroll/revoke calls should precede or follow. The schema and annotations fill some gaps, but the core invocation flow is underspecified.

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%, so the schema already explains capability, accessToken, sessionId, and enrollmentId. The description adds the same-wallet constraint and the once-only nature of the capability, but it does not explain wallet or operationId beyond their names.

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?

There is no tautology, but the description's verb is generic: 'Manage same-wallet research autopay' never says 'status', 'check', or 'query', so an agent cannot tell whether this performs a read or a management action. The name/title supply 'status', but the description itself fails to state the operation it performs.

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 gives a prerequisite ('Enrollment needs a CDP-authenticated pending reservation') but never says when to call this tool rather than otto_muse_autopay_prepare, otto_muse_autopay_enroll, otto_muse_autopay_sign, otto_muse_autopay_revoke, or otto_muse_autopay_availability. There are no explicit when-to-use or when-not-to-use conditions.

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