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

Beyond the annotations, it discloses real behavioral traits: the call can take several minutes, may be interrupted, and must be retried with the same operation_id, which gives practical meaning to the idempotentHint=true flag and tells the agent not to generate a fresh ID. It also states the return value (media_id), which matters since no output schema exists. It omits failure modes such as private/blocked links or size limits.

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?

Four short sentences, front-loaded with purpose, then rights constraint, then return value, then latency/retry guidance. Every sentence carries information the agent needs and none is redundant with another.

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 appropriately states the returned media_id, and it covers latency, retry, and legal/rights constraints for a slow network-bound import. It could be more complete by noting what happens when the URL is private, unsupported, or fails validation, but the essentials for correct invocation are present.

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%, and the one undocumented parameter (url) is the one the description explains most, by listing the accepted platform link types and the direct .mp4 case. The retry statement reinforces operation_id semantics already present in the schema, and brand_id is left to the schema, so the description adds genuine meaning rather than repeating structured fields.

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 opens with a specific verb+resource ('Descarga a la marca un video') and enumerates the accepted sources (TikTok, Instagram, Facebook, YouTube, or a direct .mp4 link), which is exactly what distinguishes it from the file-based siblings like upload_media and from publishing tools like create_post.

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?

It gives a clear eligibility constraint ('solo con videos propios del usuario o que tenga derecho a publicar') and states the downstream step ('Devuelve un media_id para create_post'), so the agent knows when this tool fits in a workflow. It stops short of naming the alternative tool to use for local files (upload_media), so the exclusion is only implicit.

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