driftguard_export_audit_report

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

No annotations are supplied, so the description carries the full burden. It does disclose meaningful behavior beyond the name: the report is digitally signed, redacted to be zero-secrets, and includes checkpoint, change, and token-telemetry sections. It does not say whether the report is written to disk, returned inline, or where the signing key comes from, nor whether it is idempotent or overwrites prior exports.

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 sentence that front-loads the verb (generate and sign) and then bounds the output contents in a compact parenthetical. No filler, no repetition of the tool name, nothing extraneous.

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 parameters, no annotations, and no output schema, the description must convey side effects and result form on its own. It covers report contents and the signing/zero-secrets guarantees, but leaves out the critical operational facts: whether it writes a file or returns content, whether signing requires configured credentials, and whether the operation changes system state.

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?

The tool takes zero parameters, which is the baseline-4 case. The description does not need to explain parameter meaning, and the empty schema is consistent with a single fixed-output export operation.

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 gives a specific verb pair ('Genera e firma digitalmente') tied to a distinct resource (Report di Conformità & Audit Trail), and the parenthetical enumerates exactly what the report contains. It is clearly separable from siblings like driftguard_budget_status or driftguard_list_snapshots, though it never explicitly names a sibling to contrast with.

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 statement of when to invoke this versus the many sibling tools (e.g., budget_status, list_snapshots, scan_secrets) that could plausibly be used for reporting or evidence gathering. An agent must infer that this is a terminal 'produce the signed artifact' step rather than a query.

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