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

Goes well beyond the annotations: it discloses credit consumption, an active narrador X subscription requirement, the narrador:x OAuth scope or nrd_x_* API key, and cached-vs-synchronous timing. The non-idempotency note adds explanation to the idempotentHint=false annotation rather than contradicting it.

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-loads purpose and return shape, then prerequisites and routing. All sentences carry information, though the auth-scope and credit details could be tightened slightly without loss.

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?

Despite having no output schema, the description names the returned fields (generationId, audioUrl, duration, wordTimings), covers auth, cost, timing model, and the polling fallback. Nothing an agent needs to call it correctly is 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 100%, so the baseline is 3. The description restates the postId/postUrl alternation already documented in the schema but adds no new syntax, format, or validation detail for accent or voiceId.

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+resource ('Generates narrador X audio for a social media post (X/Twitter)') and immediately enumerates the return payload. It distinguishes itself from the related narrador-files flow and names the sibling get_x_generation for follow-up.

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?

Gives explicit routing: poll get_x_generation with the returned generationId if slow, and call list_voices to obtain valid voiceId values. It also explains that cached results return immediately while others generate synchronously, so the agent knows when this call alone suffices.

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