Get document text

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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds a meaningful behavioral trait: the high cost/latency of this operation and the need to limit its use. It also discloses the content type (OCR/extracted text) and offline/lim support, which goes beyond the sterile schema.

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 sentences, each earning its place: the first defines the return, the second explains why this tool is separate and when to use it, the third notes pagination. No filler. The most important scoping constraint is front-loaded.

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 simplicity of the tool and the strong annotation safety profile, the description is nearly complete. It covers what is returned, the cost warning, and offset/limitt. The absence of an output schema is mitigated by 'OCR/extracted text' clearly indicating a text string. A slight gap is guidance on handling truncated output or iterative fetching, but this is minor.

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?

The schema already describes limit and offset with default/min/max values. The id parameter is self-evident given 'one document' and is not described in the schema, but the description doesn't need to elaborate. The description's mention of offset/limitt aligns with the schema without adding new semantics. With 67% schema coverage and obvious id, this hits the baseline.

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 specific verb and resource: 'Return the OCR/extracted text of one document.' It also says it is deliberately a separate tool and the most expensive thing to pull, clearly distinguishing it from siblings like get_document, get_document_thumbnail, and download_document. An agent can immediately understand what this tool does and how it differs.

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 gives an explicit usage rule: fetch this only for documents you have already narrowed down, because it is the most expensive operation. This is a clear when-to-use directive. It also implies when not to use by framing it as a last-step retrieval, though it doesn't name specific alternatvives.

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