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

Annotations already declare read-only, idempotent, non-destructive behavior, and the description adds real context beyond them: the pagination contract (has_more always present, next_offset when truncated), blank-line normalization, and that text is returned fenced as untrusted data from scanned/filed sources.

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?

Front-loads resource and windowing, then covers pagination, normalization, and trust marking in four tight sentences with no filler. Every clause carries information the agent needs.

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?

No output schema exists, and the description compensates by naming the return fields (text window, has_more, next_offset) and the untrusted-data fence. An agent can paginate and safely interpret the result without further information.

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 100%, so all three parameters are already documented, including offset as a next_offset value. The description restates the window size and default rather than adding syntax or format meaning beyond the schema; baseline 3 applies.

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 ('The extracted text of one document') plus the windowing scope, so the agent knows exactly what is returned. It does not explicitly distinguish itself from the sibling get_document (metadata vs. text), which keeps it from 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?

'Use to read a long document in order' gives clear usage context and the hearing-transcript example conveys the intended scale. No explicit when-not or named alternative (e.g., get_document for metadata) is offered.

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