youtube-download-api

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

With no annotations provided, the description carries the full transparency burden. It disclosed that the tool starts an asynchronous job, returns an id for polling, and that every call costs 1 Credit. It does not deeply document error behavior, but for a job-submission tool this is meaningful and mostly indicates that behavior.

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?

Two short sentences cover the core purpose, the asynchronous return, the polling step, and the cost. There is no fluff or repetition, and the most important details are 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?

The description gives a complete high-level lifecycle: create job, get id, poll, retrieve final URL. However, because there is no output schema and no explanation of the accept response body, a unhelpfulness for the agent to know exactly what additional fields to expect beyond the id. Still, the schema provides rich supplemental detail for all parameters.

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?

The schema already provides rich descriptions for all 10 parameters, including accepted values, defaults, duration limits, and special conditions. The description only repeats url and format without adding new syntax or semantic detail beyond the schema, so it stays at the schema coverage baseline.

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 is explicitly action-oriented: "Submits a new download job for the given `url` in the requested `format`." It also explains the unique id returned for later progress polling, which clearly separates this tool from the sibling get_ajax_progress.

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 the intended sequence: submit a job, get an id, pass it to the Progress endpoint, and poll for the final URL. It does not provide explicit when-not-to-use guidance, but the subordinate relationship to the progress tool is clear enough.

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

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

With no annotations provided, the description carries the full burden and does well: it discloses the polling nature, the exact success criteria fields (progress and download_url), and the cost implication ('Billing per call: 1 Credits'). It lacks error/failure behavior details (e.g., what happens if the job id is invalid), but the disclosed cost and polling semantics are valuable beyond the schema.

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 compact sentences, each earning its place: purpose, polling condition, and cost. Front-loaded with the core verb and resource, with zero filler or redundancy.

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 simple one-parameter polling tool with no output schema and no annotations, the description provides the essential completion criteria (progress == 1000, download_url populated), which is the single most critical piece of information an agent needs. The cost disclosure adds operational context. The polling semantics are fully specified, making the tool self-sufficient despite lacking an output schema.

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?

The schema covers 100% of the parameter with 'The job id returned by the Download endpoint,' so the description adds minimal parameter-specific value. The description does reference the response fields (progress, download_url) that the agent needs to inspect, but this is output behavior rather than input parameter deepening—baseline 3 is appropriate given full schema coverage.

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 clearly states the verb ('Polls') and resource ('status of a previously-submitted download job'), making the tool's function obvious against the sibling get_ajax_download_php. The title 'Check download progress' reinforces the purpose, though the description doesn't explicitly name the sibling as the alternative for actually fetching the download.

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 excellent when-to-use guidance with the explicit polling loop: 'Keep polling until `progress == 1000` (i.e. 100%) and `download_url` is populated.' This gives the agent a concrete success condition and termination criteria. However, it does not explicitly state when NOT to use this tool versus the sibling (e.g., when to call get_ajax_download_php instead).

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