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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuine value on top: newest-first ordering, the agency-wide scope, the pagination ceiling, and that each row exposes has_available_undo for spotting reversible operations. It stops short of describing rate limits or response shape details, but the extra context is real.

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 dense sentences, zero filler, with the core identity ('paginated audit log, newest-first') front-loaded and the payoff field (has_available_undo) placed last where it is easy to find.

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, and the description compensates by naming at least one returned field (has_available_undo) and the sort order. For a zero-required-param read tool with fully documented parameters, this is nearly complete; a hint about how expensive a large limit is or how to page forward would close the last gap.

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 the schema already documents every filter including defaults and the 200 cap; the description's restatement of tool_name/site_id/since/only_reversible/limit/offset adds almost nothing beyond it. Baseline 3 applies when structured data carries the semantics.

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+resource ('list recent receipts') and pins the scope ('audit log ... across the agency, sorted newest-first'), which is far more than the title alone. It does not, however, distinguish itself from the similar-sounding sibling fleet__list_recent_changes, so an agent must infer the difference (receipts vs. changes).

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?

The description enumerates the filters available, which implies how to narrow results, but gives no explicit when-to-use guidance or exclusions — e.g., that fleet__get_receipt should be used for a single receipt or that list_recent_changes covers a different audit surface. Usage is implied rather than directed.

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