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

The annotations only declare a generic safety profile (readOnlyHint=false, idempotentHint=true), but the description adds the operationally decisive facts: a 4-minute synchronous wait then a job_status_url polling fallback, a 20-minute audio cap, server-wide single-concurrency, and that private/login-only URLs fail. These are exactly the traits an agent needs and none are recoverable from the schema or annotations.

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?

Front-loaded with the action and return shape, then constraints, then routing to the alternative. Two dense sentences with no filler; every clause (wait/poll, audio cap, concurrency, private-content failure) carries 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?

With no output schema, the description compensates by describing the return payload (plain text plus segments with start/end times, or a job_status_url when the wait times out). Combined with the input limits and the sibling routing, an agent has everything needed to call and interpret this tool.

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, and the description goes beyond it by tying start/end to a concrete purpose (cutting videos that exceed the 20-minute limit) and by naming the target platforms for url. It still doesn't add meaning for language or translate_to_english, but the schema carries those well.

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 precise verb+resource ('Transcribe the speech of a public video, Reel, TikTok or Short') and names the underlying engine ('Whisper on the server'), so the agent knows exactly what operation runs. It also explicitly carves itself apart from the sibling get_video_info, which is the closest competitor in the toolset.

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 both positive use cases ('captions, quotes, summaries or hooks') and an explicit alternative with its selecting condition ('use get_video_info if you only need the written caption'). The 20-minute ceiling and the instruction to 'cut long videos with start/end' further tell the agent when this tool is and isn't appropriate.

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