Your webhook endpoints for watcher alerts

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses the authentication failure mode, key routing constraints, signature format, and the subtle semantics of lastError versus lastDeliveredAt, preventing misinterpretation.

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 long but every sentence earns its place, moving from what the tool returns, to auth, to exclusions, to signature and error semantics. There is no filler or repetition.

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 no-parameter, no-output-schema tool, this is complete: an agent knows what it will get, how to authenticate, what it should not use it for, and how to interpret ambiguous fields. Nothing needed for correct invocation 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?

The tool has zero parameters and the schema covers 100% of them, so there is no parameter semantic gap. Per the 0-param baseline this is a 4; the description also adds relevant context about environment variables that affect invocation.

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 identifies the tool as a read-only representation of the account's registered webhook endpoints for watcher alerts, including per-endpoint delivery and error state. It clearly distinguishes this from sibling tools by domain (webhooks vs assets/chain health/status) and explicitly says creation/rotation/deletion is not exposed here.

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 auth prerequisites (FLETCH_API_KEY with watchers:read, 401 without key, HTTPS-only delivery) and gives explicit when-not guidance: endpoint lifecycle operations are deliberately not exposed, with the dashboard and POST /api/v1/webhooks named as alternatives. This lets an agent route to the correct operation.

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