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

Annotations declare readOnlyHint=true and openWorldHint=true, and the description adds key context: the model has no memory of prior tool calls, and it returns a structured object with response/model/provider/tokens_used. It also discloses backend options and the cost-bearing max_tokens property, going beyond the annotation safety signals.

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?

The description is tight and front-loaded: a one-sentence purpose, a two-item backend breakdown, an explicit usage restriction, and a return-type signature. Every line adds information and none is redundant with the schema.

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?

Given the 7-parameter schema and annotations, the description covers the core behavior, backends, usage boundaries, and return shape. It omits error/authentication failure details, but the schema and openWorldHint already offer substantial context, so the description is sufficiently complete for invocation.

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?

With 100% schema coverage, the baseline is 3, but the description adds meaningful behavior: prompts must be self-contained because 'The model has no memory of prior tool calls,' and recommends a max ~4000 token prompt. It also clarifies which provider a glm-* model implies, complementing the schema.

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 'Routes a prompt to the best available LLM,' which is a specific verb+resource statement. It further distinguishes itself by enumerating two distinct backends (Hugging Face vs OpenVecta), clearly separating it from sibling tools that handle other x711 functions.

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 tool includes an explicit gate: 'Use ONLY when you need external LLM help. Never for things you can answer from context.' This clearly defines when to invoke. However, it does not name a specific sibling alternative tool, so it stops short of a full when-to-use comparison.

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