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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavior: the change is attributable ('records the authenticated operator') and the blast radius is bounded ('changes no other plan step'), which is exactly the kind of context annotations cannot convey. Minor gap: it doesn't say the message must still be in queued state or what the caller sees on rejection.

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 action and scope, then the preconditions, then the side-effect contract. Every sentence carries distinct information and nothing is repeated from the title or schema.

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?

Safety is well covered by the destructive annotation plus the operator-recording and no-other-step claims, and no output schema exists to explain. But for a mutation tool keyed on company/environment/case/message, the description never clarifies how those identifiers relate (e.g. that the message must belong to the given case) or what a successful cancellation leaves behind.

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 description coverage is only 20% — just the optional idempotency_key is documented — and the description says nothing about company, environment, case or message. The only inference offered is 'exact', implying the message identifier is a precise match rather than a prefix, which is a thin addition against four undocumented required parameters.

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 (cancel) and a specific resource (an exact queued Slack message), with the temporal scope 'before it starts sending'. The word 'exact' and the Slack qualifier distinguish it from summer_cases_queued_slack_list and summer_cases_queued_texts_cancel without needing to open either 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?

Explicitly states when the tool cannot be used: 'Sending, sent and uncertain messages cannot be cancelled', which pre-empts the most likely failed call. It does not, however, point the agent at summer_cases_queued_slack_list for finding the message id or explain the distinction with the texts sibling, so the routing guidance is incomplete.

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