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

With no annotations, the description carries the full behavioral burden and does so well: it discloses pagination semantics (40000 default chars, truncated flag, nextOffset loop), the 60-minute downloadUrl expiry, the edge case where no Markdown exists (markdownNote + download link only), and an explicit behavioral instruction not to fetch the URLs itself.

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-loaded with the core action, then pagination, then URL handling, then the no-Markdown fallback. Despite being dense, every sentence adds operational information an agent needs, with no filler.

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 and no annotations, the description compensates by describing the key return fields (truncated, nextOffset, downloadUrl, markdownUrl, markdownNote) and the fallback behavior. Nothing essential for correctly invoking or interpreting a call is missing.

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, but the description adds genuine meaning beyond the schema: it ties offset to the nextOffset continuation value and confirms maxChars defaults, turning independently documented parameters into a coherent pagination protocol.

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 ('Read a stored document ... as Markdown') and names the fields preserved (headings, lists, tables). It also names list_documents as the discovery sibling, so an agent can distinguish it from read_workbook and other siblings without opening any schema.

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?

It tells the agent when to reach for this tool and how to obtain the id (via list_documents or a DOCUMENT/IMAGE attribute), and explains the pagination follow-up ('when truncated is true, call again with offset = nextOffset'). It gives clear usage context but no explicit exclusions or named alternatives to avoid.

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