language_detect

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

With no annotations, the description carries the full burden and does a solid job: it discloses local execution, that nothing is stored, the per-call cost ($0.0025 USDC), and p99 latency of 300ms. What it omits is auth/payment prerequisites (does a wallet need funding?), error behavior, and any rate limit — the remaining behavioral gaps for an unannotated tool.

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?

One compact paragraph, front-loaded with purpose before params, cost and latency. The 'Language Detection —' prefix mildly restates the name, and the parameter facts are compressed into a run-on clause, but almost every clause carries information an agent needs.

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 helpfully describes the return payload (codes, confidence, reliability flag, candidates), covers both parameters, and supplies cost/latency for planning. What is missing is edge-case behavior — mixed-language or empty input, and what the 'reliability' flag actually signals.

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 largely does: it marks 'text' as required with a 20,000-character ceiling that appears nowhere in the schema, and explains 'top' as the number of candidates with its default. It fails to mention the schema's 1-10 range for 'top', and the 20,000-character limit has no stated consequence (truncation vs. error).

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 ('Detect the language of a text') and goes further by enumerating the output shape — ISO 639-1/639-3 codes, confidence, reliability flag, top candidates — and a scope of 80+ languages. It is unambiguous on its own, but it never names a sibling (e.g. translate or text_classify) to disambiguate the boundary, which is what separates a 5 from a 4 in this crowded toolset.

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?

There is no when-to-use, when-not-to-use, or alternative-routing guidance at all. An agent must infer the use case purely from the tool name. The cost and latency figures incidentally help with a cost/benefit decision, but that is not usage guidance.

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