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

Adds substantial information beyond the annotations: a new key returns signing_secret exactly once, that secret is unreadable afterward, and it must be relayed to the receiving service's operator. Annotations only declare the mutation safety profile, so this is genuinely new behavioral context about irreversibility and secret handling.

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 sentences, all load-bearing: behavior first, then the secret-handling warning, then the URL constraint. No repetition of the title or the schema's display-name boilerplate.

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?

With no output schema, the description still covers the one value that matters on return (signing_secret, shown once). Combined with the create-vs-revision semantics and the activation default, an agent has everything needed to call this correctly.

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 earns an upgrade by explaining endpoint_key outcomes (new key mints a secret, existing key creates a revision and keeps it) and by restating the HTTPS requirement on url. The activate flag's default is left to the schema, which is acceptable.

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 states a precise verb and resource and covers the dual mode ('Create a webhook endpoint or save a new revision of one'), which an agent can act on directly. Sibling differentiation against activate_webhook_endpoint_revision is only implicit (this tool activates unless told otherwise) rather than named outright.

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?

'Activate it unless activate is false' gives a clear default and the condition that overrides it, and 'The URL must be public HTTPS' is a hard precondition. It stops short of telling the agent when to prefer the standalone activate_webhook_endpoint_revision or rotate_webhook_endpoint_secret siblings.

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