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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds the substantive context: a real change re-synthesizes audio via the project's voice provider, spends synthesis credits, and replaces the old audio, while identical values are a no-op. Credit cost and the audio-replacement consequence are exactly the traits an agent needs and cannot get from the hints alone.

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?

Four tight sentences, front-loaded with the trigger condition, then the return value, then the cost/destructive consequence, then the exclusion. No filler and nothing important buried.

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?

For a mutation tool with full schema coverage and an output schema, the description covers the remaining risks: credit spend, audio replacement, no-op behavior on identical input, and scope exclusions. An agent has everything needed to decide and call correctly.

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%, and each parameter already carries its own description with constraints (lengths, language code example). The description's field list (words/translation/language/voice) merely restates what the schema documents, adding no syntax, defaults, or interaction rules beyond the baseline.

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 (change) and resource (one voiceover line) plus the exact editable facets: words, translation, language, voice. It also draws an explicit boundary against project-wide pronunciation work, so an agent can separate it from set_pronunciation_rule and create_speech without reading schemas.

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?

"Use this when someone wants to change the words, translation, language or voice of one voiceover line" gives an explicit trigger condition, and "Not for project-wide pronunciation fixes" gives an exclusion. It falls short of naming the alternative tool (set_pronunciation_rule) outright, so routing still requires a small inference.

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