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

The annotations already signal read-only, idempotent, and non-destructive behavior. The description adds important non-obvious behavioral details: the document is not persisted, sensitive identifiers are removed from the response, deterministic methods are launched immediately, and uncertain fields require confirmation. No contradiction with the annotations exists.

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?

Two dense sentences carry the full description, with the primary action front-loaded and no filler. Each clause contributes meaningful behavioral or lifecycle information.

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 the tool's complexity, the available output schema, and rich annotations, the description covers the essential workflow, data-handling caveats, and uncertainty behavior. It is slightly incomplete in routing the agent away from sibling audit/analysis tools and leaving segment and evaluation_date semantics to the schema, but it is adequate for selecting and invoking the tool.

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 only 33%, and the description partially compensates by clarifying that input can be a PDF or already-extracted text and that the document kind is bill/contract. However, it does not explain segment, evaluation_date, or how document_file and document_base64 should be selected, so the compensation is incomplete.

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 names a specific verb and resource: it extracts PDF/text of a bill/contract via the European extractor and then removes sensitive identifiers and launches deterministic methods. This is clear and distinct from a vague restatement, but it does not explicitly differentiate itself from sibling tools such as analyze_bill or decompose_invoice.

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?

The description provides a clear usage context: call this tool when a bill/contract document needs to be loaded into memory, sanitized, and immediately processed by applicable deterministic methods. However, it does not state when not to use it or point to alternative sibling tools, so routing guidance remains implicit rather than explicit.

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