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

Far exceeds the annotations: it discloses the HTTPS-only rule, SSRF/private-address blocking validated server-side, the exact delivery payload shape {event, data, occurred_at, delivery_id}, the X-OrgLines-Signature HMAC-SHA256 scheme, and that the secret is returned only once — a real footgun the agent must warn about. It also spells out the propose→confirm return contract (status='confirmation_required', action_id, plan_token) that the destructiveHint/openWorldHint annotations cannot convey.

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?

Dense but front-loaded — the resource, delivery contract, URL constraints, and confirmation behavior appear in that order with almost no filler. Some space is spent re-listing enum values already present in the schema, and the single-paragraph block with inline ALL-CAPS markers is harder to scan than it needs to be.

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?

This is a mutation tool with no output schema, so the description carries the return-value burden itself — and it does, describing the one-time secret, the status/action_id/plan_token confirmation envelope, and what each delivery looks like. Given three parameters and no nested objects, nothing an agent needs to call it correctly appears to be 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?

With only 33% schema description coverage, the description compensates well: it constrains url (maxLength aside, must be https and non-private), states that an empty events array means all events, and explains that space='personal' is required to receive intake.capture.created with ids-only bodies readable via intake_get_capture. The event enum is largely restated from the schema rather than adding syntax or filtering detail beyond it.

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?

Opens with a specific verb+resource+scope: "Register an outbound webhook for the caller's active workspace." It immediately distinguishes the resource from siblings (not delete_webhook, not create_note) and names exactly what will be POSTed to the URL, so an agent knows the effect 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?

Gives explicit operational context: it is additive, it runs propose→confirm, and the write only lands after confirm_action, which is named directly. What it lacks is a when-not clause — it never contrasts with delete_webhook or explains when a webhook is the wrong mechanism versus other notification-adjacent tools.

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