Webhook Subscriptions

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

Annotations show destructiveHint=true and readOnlyHint=false, and the description aligns with these (subscription creation/deletion is a state-changing operation). The HMAC-signed delivery note adds useful security context. However, the description doesn't disclose that delete is destructive, that URL must be publicly reachable (vs localhost), or behavior like overwriting existing subscriptions for the same URL. With annotations present, a 3 is fair—it adds context but not deep behavioral detail.

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?

Two sentences, front-loaded with the core purpose and concrete event examples, ending with the HMAC signature note. It's efficient and readable. Minor deduction: the event examples and the HMAC note could arguably be merged, but overall it's appropriately sized with no filler.

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 tool with 4 params, 75% schema coverage, no output schema, and a destructive-hint annotation, the description covers purpose, event types, and delivery security well. It's complete enough to understand what the tool does and what events it handles. It doesn't describe return/confirmation behavior, but with no output schema, the description could arguably note that listing returns subscriptions—though this is a minor gap given overall clarity.

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 75%, so the schema already documents url, id, and events reasonably well. The description adds context about what 'events' mean by giving examples of event types. However, it doesn't clarify the 'action' parameter semantics (create/list/delete) in prose, nor the id requirement for delete, nor that omitting events subscribes to all. Schema does moderate work, so 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 clearly states the tool wires webhooks to live mesh events, listing three concrete event types (call.settled, vibe.followed, capability.listed) with human-readable context for each. The verb 'wire' + 'webhook' + 'live mesh events' is specific and distinct from sibling creation tools. It loses a point for not naming the tool as subscribe/manage directly or noting it also handles listing/deleting subscriptions beyond creation.

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 explains what events the webhook receives and mentions HMAC-signed deliveries, but does not specify when to use this tool vs alternatives. It lacks exclusions or guidance on prerequisites (e.g., needing a registered node), and doesn't contrast with a poll-based or other delivery mechanism. Sibling names like mesh_follow, mesh_publish, mesh_refer suggest related but distinct actions, yet no when-to-use or when-not-to-use distinction is offered.

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