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

Annotations already cover readOnly, idempotent, non-destructive and closed-world, so the safety profile is largely pre-declared. The description still adds real context beyond them: no credit spend, and the parenthetical '(or will be) sent' hints that pending deliveries already expose their event body – useful behavior an agent could not infer otherwise.

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?

Three short sentences, front-loaded with the resource, then return content, then cost/safety. Nothing is wasteful and the important detail (full event body) appears immediately.

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 simple two-identifier read with no output schema, the description covers what is returned (the full event body) and that it costs nothing. It omits what a delivery record otherwise contains (status, attempts, response codes) and what happens when the delivery ID is unknown, leaving the agent guessing about failure modes.

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?

Top-level schema coverage is reported at 0%, and the description says nothing about the nested path object or how id and delivery_id relate. The nested properties do carry examples (`whk_12`, `dlv_9001`) in the schema, but the description does not compensate for the undocumented top-level path parameter.

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?

Names a specific verb and resource ('Get webhook delivery') and adds scope with 'One delivery with the full event body', which implicitly separates it from the sibling list endpoint dealmachine_get_webhooks_id_deliveries. It does not name the sibling explicitly, but the singular/full-body framing is enough to distinguish.

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 only implied: the mention of the 'full event body' signals this is the tool to call when you need the payload of a single delivery rather than a listing. There is no explicit statement about when not to use it, nor any routing to the list or redeliver siblings.

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