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

Substantial disclosure beyond annotations: customer-visible content warnings, subscriber notification with an hourly cap, webhook fanout for every action, append-only entries, PATCH semantics, audit retention on unpublish, and the required mcp scope plus user role. One defect holds it back: it justifies the destructive/non-idempotent hints with 'delete is one of its actions', yet no delete action exists in the enum, which could send an agent looking for one.

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?

Dense but front-loaded, with the customer-facing safety warning placed before the mechanical action list. Most clauses earn their place; the sentence restating the annotations ('Annotated destructive and non-idempotent because delete is one of its actions') is both redundant with structured fields and factually wrong.

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 nine-parameter, five-action mutation tool the description covers action semantics, side effects, auth requirements, and the read path, and an output schema exists so return values need no explanation. Nothing an agent needs to invoke an action correctly is missing.

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 100%, so baseline is 3, but the description adds meaning the flat schema cannot: it maps parameters to the action that consumes them and clarifies that title/bodyMarkdown/severity are rendered to customers. It does not, however, explain that kind's four state-advancing values interact with the separate state parameter.

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 first sentence names the specific resource (customer-facing status page incidents/publications) and explicitly contrast it with the sibling list_incidents, which returns internal incidents. Each action in the enum is then given a one-line meaning, so an agent can tell create vs publish vs unpublish apart without opening the schema.

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?

It states which parameters each action needs (create: pageIdentifier+title; add_update: pageIdentifier+publicationUid+kind+bodyMarkdown; publish: incidentUid+pageIdentifier), and routes the agent to get_status_page include=incidents for reads. That is explicit when-to-use plus the alternative read path, with no inference required.

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