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

The key side effect — "queued deliveries are dropped" — is real value beyond the annotations, which only say destructiveHint=false, idempotentHint=false, openWorldHint=true. That disclosure is exactly the kind of consequence an agent needs before calling. Note the tension: irreversible loss of queued deliveries sits oddly with destructiveHint=false, though the description is the accurate party here and it also omits whether the endpoint record itself is deleted vs merely disabled.

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 short sentences with no padding. The ordering is slightly off — the auth prerequisite leads while the actual purpose trails — but nothing is wasted and the destructive side effect is stated up front within the second clause.

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 single-optional-param tool with no output schema this is close to sufficient: purpose, auth source, and side effect are all present. It is still missing what state remains afterwards (webhook deleted vs paused), what happens if no webhook exists, and it glosses over the header-vs-api_key alternative that the schema raises.

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 the api_key parameter is already fully documented, establishing the baseline of 3. The description adds provenance ("from register_agent") but then says "Needs your api_key" while the schema marks it optional and only needed when the client cannot send an Authorization header — a mild but real inconsistency that could push an agent to pass a key unnecessarily.

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?

States a specific verb and resource: "Remove your webhook." This is clearly distinguishable from set_webhook, test_webhook and webhook_status by verb alone, though the description never names those siblings explicitly. The purpose is unambiguous without opening the schema.

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?

Usage is implied (you call this when you want to stop receiving deliveries) rather than stated, and no alternative is named — an agent must infer that set_webhook is the inverse and webhook_status is the non-destructive lookup. The only explicit guidance is prerequisite-style: get api_key from register_agent.

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