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

Annotations already cover read-only/non-destructive/open-world, and the description adds real context beyond them: the call runs against an external provider using the organization's own key, and specific preconditions produce a self-describing error. It stops short of covering latency, quota, or result-size behavior for what is a live third-party call.

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: what it returns, how to use the results, and where the input comes from plus the error case. Nothing is repeated from the schema verbatim and the most important information (what you get) leads.

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?

There is no output schema, but the description enumerates the returned fields, so the agent knows the shape. Input source, dependent sibling call, and error semantics are all present for a single-parameter read 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% and the schema already says the provider id comes from list_media_providers, so the baseline is 3. The description adds the enumerated valid provider values (HeyGen, Creatify, Synthesia) and ties the parameter to the downstream avatarId/voiceId usage, which is meaningful extra meaning.

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?

Specific verb + resource ('List the avatars ... and voices') with the scope narrowed to one provider, and it names the returned fields (id, label, thumbnail) plus the concrete provider set. It is clearly distinguishable from list_media_providers (which yields provider ids) and from sibling listing tools such as list_my_voices or list_characters.

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?

Explicitly routes the agent: provider ids come from list_media_providers, and the returned ids are used as avatarId/voiceId in generate_video. It also states the failure condition (provider without an avatar catalogue or without a configured key), so the agent knows both the prerequisite chain and the expected error case.

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