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

Since no annotations are provided, the description fully carries the behavioral disclosure burden. It clearly states that create returns the signing secret only once, warns the agent to flag this to the user. It also explains the difference in delivery format for Slack/Discord URLs versus other URLs, and explicitly marks delete as DESTRUCTIVE, noting that in-flight retries are abandoned. This is comprehensive and proactive.

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 structured as a bulleted list per action, which is highly scannable and front-loaded with the action dispatch. It is detailed but necessary, with each sentence serving a purpose (e.g., listing valid event names, explaining URL-specific behavior). Slight verbosity in the event name list is unavoidable for completeness, but the structure keeps it organized.

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?

Given the tool's complexity (multiple actions, many parameters, side effects), the description is remarkably complete. It covers all actions, required parameters, valid event names, delivery format nuances, and safety warnings. There is no output schema, but the description compensates by explaining key return values like the one-time signing secret and the lack of a rotate endpoint. An agent can safely invoke this tool in almost all scenarios.

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?

The input schema already provides descriptions for all parameters, and the coverage is 100%, so the baseline is 3. The description adds meaningful context beyond the schema, such as specifying that `id` is required for get/update/delete and that `name` is always required for create (to distinguish subscriptions). It also explains the `events` wildcard and the `isActive` pause behavior, but these are partially redundant with the schema's descriptions.

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 clearly states the tool manages outbound webhook subscriptions, with a dispatch on the `action` parameter that exhaustively lists the five operations (list, get, create, update, delete). It distinguishes itself from inbound_webhooks_manage by explicitly referencing 'outbound' and 'Groundbase POSTs to a URL,' making the direction of the webhook unambiguous.

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 provides explicit per-action usage guidance: it states when to use each action, required parameters, and special conditions such as 'Always supply a name' for create and 'Only pass the fields you want to change' for update. It also warns about the lack of a rotate endpoint and the destructive nature of delete, guiding the agent on when to avoid or confirm.

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