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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the description adds nothing on the safety or mutation profile. It also omits what the response covers, whether it is scoped to a workspace or date range, and any pagination or cost characteristics. No annotation 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?

The description is short but structurally wasteful: the endpoint path is repeated twice verbatim, and the operation ID adds no actionable information for an agent. Only the final clause about describe_operation carries signal, and it is buried at the end.

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 nested-object parameter with zero schema coverage and no output schema, the description needed to state what the overview returns and what the query object accepts. It supplies neither, offering only a redirect to describe_operation, which is a starting point but leaves the definition materially incomplete.

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% and the single meaningful parameter is a free-form 'query' object with additionalProperties unrestricted, so the schema itself conveys no parameter meaning. The description does not mention the query object at all, let alone which filters or date ranges it accepts. With two opaque parameters and no compensating text, this is a full miss.

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 restates the tool name and title verbatim ('GET /api/payment-portal/collection-overview' twice) without explaining what a 'collection overview' contains or what it is for. An agent learns only that this is an HTTP GET on a payment-portal endpoint, which it already knew from the name. No differentiation from siblings such as get_payment_portal_dashboard or get_payment_portal_payout_configs.

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?

There is no statement of when to use this versus the many sibling payment-portal endpoint tools. The single instruction, 'describe_operation provides native request schemas,' is a pointer for schema discovery, not usage guidance. An agent cannot tell from this text whether to call this or get_payment_portal_dashboard for a given question.

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