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

With readOnlyHint=true already declaring the safety profile, the description adds real value: it discloses the exact shape of the returned records, reveals that a background process ('stub') may not have finished reading a file, and states that file bodies are excluded. It does not mention result limits, ordering, or pagination for this call itself, which is a notable omission for a listing tool with no output 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?

Two short sentences with zero filler: the field inventory first, then the scope default and the sibling hand-off. Every clause — including the contents exclusion — earns its place, and nothing is repeated from annotations or title.

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?

For a two-parameter read with no output schema, the description covers the important gap by describing the returned fields, and it clarifies the read-only scope. What's missing is the operational envelope: whether the result is paged or capped, and how to combine the `paired` filter with `folderid`. Those gaps are minor but real for a listing tool an agent may call on a large corpus.

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 both parameters are already fully documented, and the description only restates the folderid default ('Omit folderid for every file') without adding anything new. The `paired` filter is not mentioned at all in the description; the schema's PROD-1302 note carries that burden entirely. Baseline 3 is correct when the schema does all the semantic work.

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 names the resource (files in a folder) and enumerates the returned fields — name, type, stub processing state, and the document classification — so the agent knows exactly what this returns. It also explicitly carves out what it does NOT do (file contents), pointing to read_file_rows. The verb 'list' is only implied by the title, and it doesn't distinguish itself from other list_* siblings such as list_documents, but the folder-file scope is specific enough.

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 gives an explicit alternative for the adjacent need: 'Contents are not returned here: read_file_rows reads what is inside one, a page at a time,' plus the default-scope rule 'Omit folderid for every file.' That routes the agent correctly between metadata listing and content reading. No explicit when-not guidance beyond the contents exclusion, and the `paired` filter's use case lives only in the schema.

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