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

Goes well past the annotations: 16MB hard limit, description is mandatory and manually authored (no AI fallback), the record becomes reachable at /api/kb/video/[id], and target_user_id is restricted to platform admins with self-account as default. These are exactly the failure modes and auth constraints an agent needs. Minor note: the tool downloads from a public URL while annotations declare openWorldHint=false, but this is consistent with the schema's own wording, so it is not a contradiction.

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 what is created and from what sources; the mandatory-description warning follows immediately. It is dense with parentheticals and runs long, but each sentence carries distinct information (size limit, endpoint, sibling tool, auth default).

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 6-parameter mutation tool with full schema coverage and no output schema, the description covers sources, limits, auth scoping, and downstream consumption. It does not state what is returned (presumably the video id/URL), which an agent would need to chain into create_whatsapp_template; the /api/kb/video/[id] hint partially compensates.

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 every parameter already carries its own explanation including the base64-over-URL priority and the admin-only target_user_id. The description's main added fact is the 16MB ceiling; most other parameter-level content restates the schema. Baseline 3 is appropriate.

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 ("Cria e indexa um VÍDEO na base de conhecimento") and immediately distinguishes it from the sibling create_kb_image ("Diferente de imagem, não existe descrição automática"). It also positions the artifact relative to create_whatsapp_template (header_video_url), so an agent can place it in the tool graph without opening the schema.

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 concrete usage contexts (send during active conversations, use as header_video_url in prospecting cadences) and the source alternative (public URL vs base64 when nothing is hosted). It stops short of an explicit exclusion (when NOT to create a KB video, e.g. reuse an existing one via list_kb_documents), so it is clear context rather than a complete decision rule.

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