Language token tax

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

With no annotations, the description carries the full burden; it implies a read-only lookup by framing the output as a per-model measurement and enumerating the covered models, which reassures the agent nothing is mutated. It does not say whether the values are static measurements or live computations, nor anything about return shape (ratios, percentages, table structure).

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 clauses, with the metric definition front-loaded and followed by scope and the omission rule; nothing is padded. Naming four model families costs some space and partly duplicates list_models, but it usefully fixes which models the numbers apply to.

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?

For a single-parameter lookup with no output schema, the description covers the metric, model coverage, language coverage, and no-filter behavior. What is missing is the return shape — whether each model yields one ratio, a percentage, or a richer record — which an agent may need to interpret results since no output schema exists.

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 the schema already documents name-or-code examples, so the baseline is 3. The description adds the default behavior when the parameter is omitted ('list all'), which the schema does not express despite the parameter being optional — genuine meaning beyond 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 states a precise, unusual metric — how many more tokens the same text takes in a language than in English — plus the measured models and language count. This is far more than a restatement of the name, though it never contrasts itself with siblings like estimate_text_cost or compare_models, which an agent might otherwise reach for.

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?

It gives one concrete usage rule: 'Omit language to list all,' which tells the agent how to use the optional parameter as a discovery mechanism. It offers no guidance on when to prefer this over estimate_text_cost or compare_models, so selection among siblings is left to inference.

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