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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds that the tool returns extracted readable text and that unsupported documents are rejected, which is useful, but says nothing about failure modes for missing documents, size limits, or whether the extraction is lossy.

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?

The core operation and the covered document types are front-loaded in one efficient sentence. The bare API URL adds little and the refusal sentence is terse, but there is no padding or redundancy.

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?

A four-parameter tool with nested objects, 0% schema coverage and no output schema needs the description to carry more weight. It never explains how to identify the document or supply connection context, and it leaves the overlap with a dozen document-reading siblings unresolved.

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% across four parameters, and the description does not mention any of them. Critically, the required operation_id is never explained — the agent must infer that it identifies which document to read, and nothing clarifies company_key, path_params or query_params.

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 concrete verb and resource ("Return the text of a document") and enumerates the covered document types (invoice/offer/order PDF, SIE, archive, inbox). That is far clearer than the title alone, though it does not explain how it relates to the many near-identical siblings like read_invoice_pdf or read_sie_file.

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 only usage constraint is the negative one, "Any other document is refused," which scopes document types but not tool choice. With siblings such as read_invoice_pdf, read_offer_pdf, read_sie_file, read_archive_file and read_documents all plausibly applicable, the description should say when to pick this generic reader instead of the specific one.

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