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

Goes well beyond the readOnly/openWorld annotations by disclosing three non-obvious traits: the default is the ORIGINAL spoken track rather than TikTok's first-listed track, a language miss errors out with a list of available tracks instead of silently substituting, and the call costs 1 credit. These are exactly the failure modes and costs an agent needs before invoking.

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?

Five short sentences, front-loaded with what is returned, then default behavior, then error behavior, then cost. Every sentence carries distinct information and the rationale clause ('so the text reflects what was actually said') justifies the default rather than padding.

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 no output schema, the description usefully characterizes the return value ('one text block plus timed cues') and covers cost and error behavior for a 3-param read tool. The only omission is any explanation of cache_max_age.

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 67%, so url and language are already documented. The description adds real value for `language` (default semantics and the hard-error-on-miss behavior), but `cache_max_age` is undocumented in both the schema and the description, leaving a gap the prose doesn't compensate for.

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 resource and output shape: 'The spoken transcript of a TikTok, as one text block plus timed cues.' An agent immediately knows this is the text-extraction counterpart to tiktok_video's metadata. It doesn't explicitly name sibling tools, so it falls short of a 5.

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?

Usage guidance is implied rather than stated: 'Pass `language` for a specific track' tells you how to select a non-default track, but there is no explicit when-to-use-this-vs-tiktok_video or when-not guidance, and no mention of prerequisites (e.g. whether the video must have captions).

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