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

Annotations already declare destructiveHint=true, but the description adds genuinely non-obvious behavior: TTS quota consumption, that pre-existing audio is kept unless existing='replace', and that texts with a video or YouTube link are always left untouched. The keep/replace mechanics are partly restated from the schema enum, which slightly caps this score.

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 single dense paragraph is front-loaded with the most important constraint (only on explicit user request) and every sentence carries distinct information, so nothing is padding. It is, however, a run-on block that would be easier to parse as short bullets given 8 parameters.

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 explains the return value ('generated' lists every text that got audio, with its element and item). Combined with the quota warning, the preservation rules, and the mapping guidance for all 8 parameters, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description adds real interpretation: it maps the user's phrasing onto 'elements' via media_targets.audio ('the questions' = question, 'the answers' = choice, 'everything' = every element), and explains how 'answers', 'positions', 'selection', and 'listed_texts' interact with what the user said.

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+scope: 'Generate the spoken audio of a part of the activity and save it into its texts.' This clearly separates it from siblings like attach_video, illustrate_items, and describe_image, which handle different media types.

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 an explicit hard precondition ('Call it ONLY when the user asked for audio in their own words') and an explicit prohibition with rationale ('never add audio on your own initiative, not even to finish an activity you have just written'), because generation spends the user's TTS quota. This is exactly the when/when-not guidance an agent needs to avoid over-calling.

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