Retry a voice-note transcription

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

Annotations (destructiveHint=true, idempotentHint=false, openWorldHint=true, readOnlyHint=false) carry the safety profile, and the description adds real substance beyond them: the idempotency-key requirement and server-side key generation, the required scopes, and the enumerated refusal causes. It does not explain what 'destructive' actually means here — whether an existing transcript is replaced or discarded — which is the one gap an agent would care about given destructiveHint=true.

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 action and its negative scope, then failure modes, then operational metadata; nothing is wasted and each block serves a distinct purpose. The Luca operation/scope boilerplate is dense but functional for an agent that must supply a key and scope.

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?

With an output schema present, return values need no explanation, and the description covers the risky parts an agent needs: idempotency, scopes, workspace override, and failure modes. The only missing piece is the effect on any existing transcription, given destructiveHint=true.

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 only 50%, so the three required UUIDs (id, messageId, mediaId) have no schema descriptions; the description compensates by spelling out the REST path template, which maps each required id to conversation/message/media. It also explains idempotencyKey fallback behaviour and the workspaceId/workspaceSlug override, though much of that duplicates existing schema descriptions.

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?

The first sentence names a specific verb and resource ('Queue another transcription attempt for a voice note') and scopes it to the conversation context, which an agent can act on. It does not, however, distinguish itself from near-neighbours in the sibling list such as luca_review_queue_media_retry or luca_conversations_partial_send_retry.

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?

'Queue another transcription attempt' implies the trigger condition (a prior attempt failed or is unusable), and 'Only re-transcribes; never drafts or sends' rules out send/reply tools. But there is no explicit when-to-use statement, no routing to an alternative (e.g. the review-queue media retry), and the three refusal conditions are consequences rather than pre-call guidance.

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