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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds valuable behavioral context: it explains the meaning of has_transcript false (common, not an error), which prevents an agent from treating a missing caption track as a failure. It also describes the output as 'one joined string plus timed cues', giving a clear picture of the return shape. It does not mention rate limits or pagination, but for a read-only transcript tool this is a minor gap.

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 description is two sentences with no wasted words. The first sentence states the core purpose and output shape, and the second sentence clarifies a common edge case (has_transcript false). Every sentence earns its place, and the most important information is front-loaded.

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 read-only transcript tool with 100% schema coverage and no output schema, the description is nearly complete. It explains the output shape, the meaning of a missing transcript, and the expand parameter's trade-off is already in the schema. The only minor gap is that it doesn't explicitly state what happens when lang is omitted (the schema says 'Omit to get the original track', which covers it). Overall, an agent has everything needed to call this tool 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%, so the schema already documents all three parameters (id, lang, expand). The description adds meaning beyond the schema by explaining the output structure ('one joined string plus timed cues') and the semantics of has_transcript false, which helps an agent interpret the response. The expand parameter's behavior is fully documented in the schema, and the description reinforces the compact-vs-complete distinction. The description does not add much about lang, but the schema already covers it.

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?

The description states a specific verb and resource: it retrieves a video's spoken text from TikTok's own caption track, and specifies the output shape (one joined string plus timed cues). It also clarifies the meaning of has_transcript false, which distinguishes this from a generic transcript tool. The title 'Video transcript' is consistent and the description adds detail beyond the title.

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?

The description explains when to use the tool (to get a video's spoken text from TikTok's caption track) and clarifies that has_transcript false is common and not an error, which helps an agent avoid misinterpreting a missing transcript. It does not explicitly name sibling alternatives or state when not to use this tool, but the sibling list shows many other TikTok tools with distinct purposes, and the description's specificity is sufficient for most selection decisions.

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