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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description goes well beyond them: deliveries stop, the watch cannot be recovered, the cap_ prefix silently redirects to a different object whose alert emails also stop, and a key (or OAuth for cap_ ids) is required. That is exactly the extra behavioral context the annotation bar asks for.

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?

Front-loaded with the destructive action and consequence, then branching behavior, sourcing, and the anti-use case. Dense but nearly every clause carries information; the quoted 'stop watching this' is mildly decorative but serves intent routing.

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?

An output schema exists so return values need not be described. Everything an agent needs before calling — irreversibility, credential requirement, sibling source of the ID, cap_ special case, and the no-pause caveat — is present.

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% for a single parameter, so baseline is 3, but the description adds real semantics the schema lacks: the cap_ prefix changes the target object and the credential mode, and the ID's provenance is given. Not a 5 only because no format/validation detail is offered for the identifier itself.

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 ('permanently retire a registered standing intent (webhook watch) by intent_id') and immediately distinguishes the cap_ variant, which retires a Capacity Source requirement instead. An agent can tell exactly what is being removed and how it differs from the sibling list_standing_intents / register_standing_intent pair.

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?

Explicitly names the trigger intent ('stop watching this'), the way to obtain the identifier ('Get the intent_id from list_standing_intents or from the register response'), and an explicit exclusion ('Do NOT use to pause temporarily; there is no pause'). This is the full when/when-not/where-from triad.

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