get_transcript

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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds value beyond that by disclosing the transformation behavior: the text format strips cue numbers and timestamps, while 'vtt' keeps timings. This helps the agent predict exactly what will be returned, though it does not cover edge cases like missing tracks or invalid language codes.

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?

Three tight sentences with no filler. The first sentence states the core action, the second explains the output transformation and use case, and the third gives the format-switching instruction. Every sentence contributes distinct information.

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, single-resource fetch tool with three well-documented parameters and no output schema, this description is complete: it states what the tool returns, how to request the alternative format, and how track selection works. The annotations cover safety and idempotency, so nothing essential 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 coverage is 100%, so the baseline is 3. The description adds a bit more meaning by framing the 'text' format as the summarized/repurposable output and explicitly tying 'vtt' to retaining timings. It also reinforces the language/active-track behavior, giving the agent a clearer mental model than the schema alone.

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 pair: 'Get a video's transcript as plain readable text.' It also clarifies the output form ('words only, with cue numbers and timestamps stripped') and the track-selection behavior, which sets it apart from track-management siblings like list_texttracks and delete_texttrack. This is a clear, non-tautological purpose statement.

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?

Provides clear intended-use context: 'which is what you want for summarizing or repurposing.' It also tells the agent to use format 'vtt' when timings must be preserved. It does not explicitly name alternative tools or state when not to use it, so it stops short of full exclusion guidance.

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