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

Annotations only declare readOnlyHint=true; the description adds default window sizes (500 rows, 10 pages), index conventions (zero- vs one-indexed), and the truncated=True continuation behavior. It gives no details on result content or errors, but that is a minor gap given the read-only safety profile.

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?

Every sentence earns its place: purpose, trigger condition, file-type-specific pagination rules, and truncation handling. It is front-loaded with the core action and avoids restating schema field descriptions.

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 7 parameters, no output schema, and only readOnlyHint, the description covers the essential use cases and pagination behavior. Missing a precise description of the returned content format is a gap, but the guidance around truncated=True and parameter defaults makes the tool callable without further inference.

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 the baseline is 3, and the description adds meaningful grouping: it tells agents which parameter family applies to which file type and what the default windows are. It also reveals the truncated flag, which informs how the agent should set page_start next, going beyond the schema.

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 ('read') and resource ('any file in the user's attachment library') with a slicing mechanism ('by id'). The phrase 'When the result has truncated=True, advance page_start' reinforces that it is a paginated read operation, and 'any file' helps separate it from email-specific attachment readers.

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?

Explicitly says to use it when the attachment summary doesn't contain enough data to answer. It also provides concrete pagination instructions (row_start/row_end for spreadsheets, page_start/page_end for PDFs/PPTX/text) and a continuation rule for truncated results. It doesn't name alternative tools or state when not to use it, but the context is clear.

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