Retry unsent message parts

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 bar is lowered. The description adds real value beyond that: required OAuth scopes (conversations:write, luca:queue_ops), data sensitivity, the server-side idempotency-key generation fallback, and the fact that the call is rejected without confirm. It does not, however, describe what partial-failure state is left behind or revocation semantics.

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?

The purpose is front-loaded in the first sentence and the following lines are short, scannable operational facts (endpoint, scopes, idempotency, confirm, workspace override). Some lines duplicate structured metadata (e.g. endpoint and the confirm requirement also appear in the schema), which is minor waste but not egregious.

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 not be explained. For a destructive, scope-gated tool the description supplies scopes, idempotency, confirm, and workspace override — nearly everything an agent needs to invoke it correctly. Only deeper failure/reversibility semantics are missing.

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 67%, so the baseline is 3. The description restates what the schema already documents for idempotencyKey (auto-generation when omitted) and confirm, and adds the workspace override intent, but it does not clarify the required id/messageId beyond the UUID schema, leaving marginal added meaning.

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 (retry) and a precise resource scope ('only the parts of a partially sent message that are known not to have reached the provider'), which clearly separates it from luca_conversations_send and luca_conversations_messages. The endpoint annotation 'POST /api/conversations/{id}/messages/{messageId}/retry' reinforces what it operates on.

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?

Clear context for use: retry only the unsent portions of a partially delivered message, and the description states the precondition for safe retries (idempotencyKey) and the mandatory confirm: true. It does not explicitly name alternatives (e.g. luca_conversations_send for full resend) or when-not-to-use it, so it falls short of explicit routing.

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