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

Goes well past the annotations: it discloses per-call pricing ($0.01 via x402 USDC or a card key), the 25 free calls, that failed calls are free, and that repeats are not free — which explains the idempotentHint=false in billing terms rather than merely restating it. It also explicitly confirms the readOnly/non-destructive profile ('Reads or computes only and changes nothing'), adding auth/payment context the annotations do not carry.

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 the output contract, then uses, then a concrete input example, then cost. Dense but nearly every sentence carries distinct information; the example and pricing sentence are both functional, though the example is marginally expendable.

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, and the description compensates by describing exactly what is returned and its dimensionality. Input limits, language coverage, cost model and side-effect profile are all covered, so an agent has everything needed to call it correctly.

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 there is only one parameter, so the schema already documents `text` fully. The description's 'up to 4,000 characters' and the inline example echo that, adding format intuition but no genuine semantics beyond 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 with the exact output shape (1,024-dimension vector for up to 4,000 characters, 100+ languages) and names the underlying model BGE-M3. This makes it trivially distinguishable from generative siblings like ai_chat, ai_summarize_text or ai_classify.

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 lists intended uses: semantic search, RAG retrieval, clustering, deduplication. However it gives no when-not guidance or comparison to alternatives such as ai_classify or ai_keywords, so an agent must infer that embeddings are for vector/retrieval work rather than labeling.

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