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

Annotations already establish a safe read-only, idempotent behavior, and the description adds genuinely new context: the placeholder-key requirement ('The request uses $CHINAAPI_KEY; never put a real key into it') and the fact that video recipes include a distinct polling step. It stops short of stating rate limits or whether the tool itself performs the polling.

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 sentences, zero filler, and front-loaded with the list of returned artifacts so the agent knows the payload shape immediately. The security constraint closes the description rather than cluttering the opening.

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 correctly compensates by enumerating the return contents (endpoint, headers, body/form, curl, polling step). It does not clarify whether the polling step is executable code or descriptive text, a minor residual gap for a recipe-generation 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 description coverage is 100%, so the schema already documents model, agent, protocol, and capability with enums and defaults; the description adds only marginal framing (agent config is optional, model must match list_models output). Baseline 3 is appropriate when the schema carries the parameter burden.

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 and resource ('Get a runnable request for one model') and enumerates the concrete artifacts returned: endpoint, headers, JSON body or multipart form, a curl command, and the video polling step. This is clearly distinguishable from siblings like chinaapi_list_models or chinaapi_estimate_cost without opening any 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?

Usage is implied rather than stated: the agent can infer it needs an exact model ID from chinaapi_list_models first, and the optional agent parameter reveals a configuration-retrieval mode. But there is no explicit when-to-use/when-not guidance or direct comparison to the sibling tools, leaving the agent to infer the call sequence.

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