Dismiss a failed reply

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description reinforces these with concrete meaning: removal propagates to every device, nothing is sent, and repeat dismissal is a no-op. It also surfaces auth requirements (conversations:write, luca:queue_ops) and data sensitivity. The only gap is whether dismissal is recoverable/undoable.

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 human-meaningful behavior in two short sentences, then cleanly separated operational metadata (endpoint, scopes, sensitivity, workspace override). No sentence is redundant with the name or title.

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 no explanation, and the description covers scope, idempotency, cross-device effect, and workspace override. It is slightly incomplete in not noting recoverability or pointing to the retry alternative.

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 50%: workspaceId/workspaceSlug already have their own descriptions, which the description largely repeats. The description does not explain the two required params directly, though the embedded POST path 'conversations/{id}/reply-failures/{failureId}/dismiss' implicitly disambiguates id as the conversation and failureId as the reply failure.

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 (close/dismiss) and resource (a failed reply) plus the observable effect: it leaves the thread on every device. The phrase 'the coach has given up on' implicitly separates it from retry siblings, but no sibling is named, so differentiation is inferred rather than explicit.

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?

'the coach has given up on' implies when to dismiss rather than retry, and 'Sends nothing' rules out confusion with send tools. However, it never names the alternative (luca_conversations_reply_failure_retry) or states any when-not-to-use condition, leaving the agent to infer the routing rule.

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