Summarize what changed in a period

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety credit is partly pre-paid; the description earns its share by disclosing the response envelope, ISO 8601 time formatting, and a truncation contract (omitted counts plus a 'narrow' hint for requesting less) that annotations could never convey. It does not discuss cost or size limits quantitatively, so it falls short of a 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?

Three sentences, front-loaded with the effect, then routing to siblings, then the return shape. It is dense — the second sentence packs the full object shape, status enum and FK relationship into one long clause — but nearly every clause carries information; only minor tightening is possible.

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 must describe returns, and it does: documents with path/status/from/to and values with document/reference/before/after/at, plus truncation metadata. Combined with annotations, an agent has everything needed to call and interpret it.

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%, including the date-vs-datetime parsing rules and defaults, so the schema already carries parameter meaning. The description only restates the period framing and ISO 8601 times, adding no new syntax or edge-case guidance beyond one example's spirit — appropriate baseline for full schema coverage.

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 states a specific verb and resource — summarizing everything created, changed or removed in the served folder, plus embedded values that moved — and immediately distinguishes itself from folio_changes (per-reader) and folio_history (single document versions). An agent can choose among the three without opening any 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?

It gives explicit selection criteria ('what changed this week or since a date across the whole folder, read or not') and names both alternatives with the condition that picks them instead. Coverage of read vs. unread and whole-folder vs. per-reader scope removes the main ambiguity an agent would have.

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