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

With no annotations, the description carries the full burden and does substantial work: batch limits (100 texts, 8,000 chars each), billing per started 1,000 tokens with a concrete price, and the Authorization: Bearer charging model. It does not cover failure modes (e.g. what happens if both text and texts are sent, or if neither is) or truncation behavior on oversized input.

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?

Dense and front-loaded: capability, limits, cost, auth, then parameters in one compact block. The telegraphic style ('Billed per started 1 000 tokens') is efficient, though the billing sentence and parameter list are packed tightly enough to read as a spec dump rather than a description.

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?

An output schema exists, so return shape need not be explained, and the description still covers the dimensions an agent needs (vector size, normalization, language coverage, batch limits, cost). What remains missing is input validation behavior and whether text/texts can be combined, which matters given zero required parameters.

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 0%, so the description must compensate, and it does: text is a single text, texts is a JSON array of texts as an alternative, and kind takes passage (default) or query. This even clarifies that texts is an array, which the schema's string type does not convey. Only the mutual-exclusivity / at-least-one requirement is left implicit.

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 concretely what is produced: 384-dimensional normalized vectors for search and RAG, across 50 languages. The verb is implied by the name but the output and resource are unambiguous. It does not name a sibling such as semantic_search to draw the line between generating embeddings and searching an index, so it falls short of a 5.

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 through the 'search and RAG' framing and the passage-vs-query distinction, which suggests indexing documents versus embedding a query. There is no explicit when-to-use/when-not-to-use guidance and no named alternative among the many siblings (semantic_search, classify, etc.).

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