create_webhook

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

With no annotations provided, the description carries the full behavioral burden, and it delivers: 'Returns the endpoint AND its signing secret (shown only once)' is a critical disclosure — an agent must capture the secret on creation because it won't be shown again. The description also discloses the https endpoint constraint and the user-confirmation requirement. It does not cover auth permissions, idempotency, or duplicate-creation behavior, but for a create tool the one-time-secret warning is the most important trait and it is clearly stated.

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?

Four short sentences, each carrying distinct load: the action, the URL constraint, the critical return-value behavior, and the call precondition. The description is front-loaded with the action sentence. The only minor cost is that the https constraint partially repeats the schema's url description, but for a security-critical constraint this redundancy earns its place.

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 3-parameter tool with no output schema and no annotations, the description covers what an agent needs to call correctly: what it creates, the URL requirement, the shape of the return (endpoint + one-time secret), and the consent precondition. Remaining gaps are minor — the optional 'description' parameter is undocumented in both schema and description, and the events parameter's format is delegated to a sibling tool via the schema rather than the description.

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 67% (url and events are documented in the schema; description is not). The description adds little beyond the schema: 'public https endpoint' restates the url schema description, and 'one or more events' restates the minItems:1 constraint. It does not clarify the undocumented 'description' parameter, so it neither fully compensates for the coverage gap nor meaningfully extends the schema semantics. Baseline 3 is appropriate.

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 opens with a specific verb+resource: 'Create a webhook endpoint subscribed to one or more events.' This clearly distinguishes it from siblings like update_webhook, delete_webhook, list_webhooks, and rotate_webhook_secret by naming the create action and the resource. The additional constraints (public https URL, one-time signing secret) sharpen the purpose further.

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 one explicit precondition — 'Only call after the user confirms' — which is genuine usage guidance. However, it does not name alternatives or exclusions, such as directing the agent to update_webhook for modifying an existing webhook or to list_webhook_event_types for valid event names (that pointer lives only in the schema, not the description). Usage context is implied rather than explicit.

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