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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing cost (3 credits per successful call), that billing only occurs on success, and that schema-invalid input is rejected before billing. It also names the fixed model and dimension count, so the agent knows the output is deterministic in shape.

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 compact sentences: capability and model first, return shape second, cost/validation third. No filler, and the most decision-relevant facts (limits, price, failure billing) are all surfaced.

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?

No output schema exists, but the description supplies the return shape ({ model, dimensions, count, vectors: number[][] }). Combined with cost and validation behavior, an agent has everything needed to call this correctly for a single-parameter 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?

There is one parameter and schema coverage is 100%, with the schema already documenting '1 to 16 texts, each up to 2000 characters.' The description's batch bound restates the schema rather than adding new meaning such as truncation behavior for over-length input.

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 ('Embeds'), the exact resource ('1 to 16 short texts'), the fixed model (@cf/baai/bge-base-en-v1.5) and output dimension count. The stated intent ('for search and clustering') also separates it from comparison siblings like similarity and find-similar.

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?

'for search and clustering' implies the downstream use case, so an agent can infer this is the vector-generation step. However, it never explicitly says when to pick this over siblings such as similarity or find-similar, nor does it state prerequisites or follow-up steps.

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