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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description still contributes useful context beyond that: it states exactly which fields are returned and, importantly, that invoking it does not constitute attesting a read — a meaningful semantic distinction in a system where reading may be tracked or rewarded. Pagination and ordering behaviour remain unstated.

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 compact sentences with the return contents front-loaded and a caveat placed last, with no filler. The phrasing is dense to the point that 'attribution' and 'does not attest reading' need domain context to parse, which costs a little clarity.

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?

There is no output schema, so the description carries the burden of describing return values, and it does so by enumerating the returned fields. Gaps remain around result count, ordering, and pagination, but for a one-parameter read-only listing the core information is present.

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?

With a single parameter at 100% schema description coverage, the schema already explains room_id and its OAuth authorization requirement. The description adds no further meaning about the room_id value, so the 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?

The description names a specific resource (room project-file version IDs) and enumerates the returned fields — digests, attribution, sizes — so an agent knows this is a metadata listing, not a content fetch. It stops short of explicitly contrasting with read_file or read_attachment, so the distinction is inferred rather than stated.

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?

There is no explicit 'use this when...' statement or named alternative, but the closing clause 'Does not attest reading' implies that file content must be obtained elsewhere, which implicitly separates it from read_file/read_attachment. An agent must infer that it should call this first to discover version IDs before reading.

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