Show recent changes

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

Beyond readOnlyHint/idempotentHint, it discloses that results come from one complete walk, defines changedAt as the newer of original mtime and upload time, warns that an incomplete walk never overwrites a snapshot and omits removed/moved entries, and notes the plaintext file list lives in a local index folder. The closing 'Changes nothing on Drive' explicitly reconciles the mutation-flavored 'save' mode with the readOnly annotation rather than contradicting it.

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?

A single dense paragraph that front-loads the default behavior and then the opt-in snapshot mode. Every clause carries information — date grammar, ordering, baseline semantics, failure behavior — with no repetition of the title or 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?

For a five-parameter, all-optional read tool with no output schema, the description covers mode selection, ordering, limit scope, prerequisite configuration, and degenerate-case behavior. An agent can choose a mode and call it correctly without consulting anything else.

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 baseline is 3, but the description adds real meaning: the `since` grammar plus its 7d default, and the precise semantics of 'diff' vs 'save' including the same-size-and-sha1 heuristic for detecting moves. The interaction rule that `since` cannot be combined with snapshot is reinforced beyond the schema's brief note.

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 opening clause 'What changed under a path' states a specific verb+resource and immediately separates this from plain listing tools like drive_list or drive_tree. The two operating modes (default time-window scan vs. snapshot diff) are named concretely. It stops short of naming a sibling alternative explicitly, so it lands at 4 rather than 5.

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 a clear decision rule: omit snapshot for a since-based change feed, use snapshot:'diff' to compare against a stored baseline, and 'save' to also rebaseline. The prerequisite (PROTON_DRIVE_INDEX=1) and the mutual exclusion of `since` with snapshot are stated. No explicit when-not guidance or named sibling alternative, so not a 5.

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