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

With no annotations present, the description carries the full burden and does a solid job: it discloses pricing (€0.001/request), the ×3 surcharge for llm mode, the 20,000-character ceiling, the auth mechanism (Bearer API key), and that returned positions are recomputed against the source text. It omits failure behavior (e.g. what happens if both text and url are supplied, or if url fetch fails), so it is not exhaustive.

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 but well ordered: mode behavior and constraints first, then cost/auth, then a compact parameter glossary. No sentence is filler, and the terse 'Parameters —' block keeps the body short while still documenting every input.

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?

Given an output schema exists, the description is not obliged to explain return values, and it still gestures at them via the note on recomputed positions. For a paid, dual-mode extraction tool with five optional parameters it covers cost, limits, auth, and per-mode semantics adequately; edge-case and error handling are the only meaningful gap.

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 largely does: it documents all five parameters, including that url is an alternative to text, that types is a comma-separated keep-list in ner mode (default all six) but required in llm mode, and that language is ISO-2 with auto-detection. It could be clearer on whether url triggers a fetch and how text/url precedence is resolved.

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 (entity extraction) and enumerates the concrete entity classes for the default mode, plus a second mode for custom types. An agent knows exactly what the tool returns. It does not differentiate itself from nearby siblings such as contract_clause_extract or table_extract, which keeps it off 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?

Gives real selection guidance between the two internal modes: use ner for the six built-in types in en/de/ru/uk, use llm when you need your own types in any language — with the explicit cost consequence (×3). It stops short of saying when to prefer this tool over sibling extraction tools, so no exclusions are provided.

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