buzz_files

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so "Read-only; nothing is downloaded" largely reinforces structured data rather than adding new information. The one genuine behavioral disclosure beyond the schema is that limit counts messages scanned, not files returned, which matters for interpreting sparse results. No mention of how results are ordered or whether the scan stops early.

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 sentences, front-loaded with the action and the returned fields, followed by the safety note and the parameter caveat. No filler, and the most decision-relevant information (what you get back) comes first.

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 correctly compensates by enumerating the returned fields and stating that no files are downloaded; the follow-up pointer to buzz_attachment_read closes the workflow loop. It is slightly thin on scan semantics such as ordering or whether older files beyond the scanned message window are omitted.

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%, and the description's limit explanation ("messages scanned, default 200, max 500") duplicates the schema text verbatim rather than extending it. The channel parameter accepts a name or id per the schema but the description adds nothing about DM addressing or resolution behavior. Baseline 3 applies when the schema already carries both parameters.

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 ("List the files shared in a channel (or DM)") and enumerates exactly what each row contains: filename, type, size, sharer, timestamp, plus the message id and index. It also implicitly separates itself from buzz_read (messages) and buzz_search by being file-oriented, so an agent can pick it without opening a 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?

Gives clear usage context: use it to enumerate shared files and then route to buzz_attachment_read with the message id + index. It stops short of explicit exclusions (e.g., use buzz_search for text search, or that DMs share this same tool rather than buzz_dm_read), so it is clear but not fully alternative-aware.

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