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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description adds ordering ('newest first'), provenance of update-attached files (they 'stay on their update and are listed here with its id'), and the fact that content is metadata not bytes. It does not discuss pagination/limits, though the schema does, so a 4 rather than 5.

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?

Dense but front-loaded: the resource and ordering lead, followed by what is returned, then the routing caveat. The first sentence is clause-heavy and slightly run-on, but virtually every phrase carries information (provenance, return fields, alternative tool, slug source).

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 must cover return values and it does — names, types, sizes, and the text-extracted flag, plus the explicit 'not the bytes' caveat. Only pagination/total-count expectations are left implicit, which keeps it short of 5 for a list tool.

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; the description earns more by explaining that the slug is a company or pitch slug sourced from list_companies/list_pitches/search_companies, which the schema only labels generically as 'The company's or pitch's slug.'

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 documents in a company's or pitch's data room') plus scope: files uploaded directly and files attached to founder updates. It also distinguishes itself from the sibling `search` tool, so an agent can route between them without opening schemas.

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 'search with type files' to find a document by its content, and tells the agent where the required slug comes from (list_companies / list_pitches / search_companies). Both the alternative and the prerequisite are spelled out.

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