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

Beyond the readOnly/openWorld annotations, the description discloses real behavioral traits: content is transcribed from rendered pixels (so tables/scans become text), untranscribed pages appear as marked holes the agent should surface rather than skip, and the returned `covered` range may be wider than the requested range. These are non-obvious traits an agent cannot get from the annotations or 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 short paragraphs, front-loaded with the core action, then behavior, then the citation rule. Every sentence carries operational weight — no filler, no restatement of the name.

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?

With no output schema, the description carries the return-format burden and does so: markdown output, hole markers for failed transcription, and the `covered` field semantics. Combined with the schema's 40-page clamping note, an agent has everything needed to call and interpret this tool correctly.

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 100%, so the baseline is 3, but the description adds meaning about how the requested page inputs relate to the returned coverage ('covered may be slightly wider than what you asked for; cite the page numbers in covered, not requested'). That is genuine semantic value for interpreting first_page/last_page behavior, above the schema 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 opens with a precise verb+resource+scope: 'Read a page range of a document as markdown.' That distinguishes it from whole-document retrieval, and the second paragraph clarifies it works from rendered pixels. However, it never names sibling tools like get_document or search_documents to make the boundary explicit, so differentiation is inferred rather than stated.

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?

Usage context is implied (you call this to read pages of an already-known document) and there is useful operational guidance on handling transcribed holes and on citing `covered`. But there is no explicit statement of when to prefer this over get_document or search_documents, and no stated prerequisites beyond the schema's document_id provenance hint.

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