get_audit_details

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

Annotations already establish read-only/non-destructive, and the description adds real behavioral context on top: old/new values are withheld by default and only projected on explicit opt-in, projection is bounded and heuristically masked, and detail vs. summary permissions are reported separately. That is genuine disclosure beyond the structured fields, though the truncation/masking mechanics stay at a high level.

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 with no filler, but the opening clause 'Read native bound RetrieveAuditDetails' is low-information jargon that pushes the actually useful content (opt-in bounded values, separate permission reporting) behind it. Front-loading is weak for an agent skimming definitions.

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 should convey something about the return shape, yet 'other detail types are named without fabricating unsupported fields' and 'summary metadata' remain undefined. It covers the value-withholding behavior adequately but leaves an agent guessing what a response actually contains.

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 83%, so the schema already explains include_values, max_text_chars, and the aliases; the description mostly restates the opt-in/bounded semantics in prose. It adds the useful note that unsupported fields are named rather than fabricated, but no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 verb 'Read' and the resource ('audit details' plus 'audit summary metadata') are present, but the phrasing 'native bound RetrieveAuditDetails' is opaque API jargon rather than an agent-readable statement of what comes back. It never distinguishes itself from the sibling get_record_audit_history, so an agent must infer that this is per-audit-entry detail while the sibling is per-record history.

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 explicit when-to-use or when-not guidance, and no mention of get_record_audit_history as the alternative for listing a record's audit trail. The only implicit usage signal is 'opt-in' on attribute values, which tells the agent a flag exists but not when this tool is the right choice.

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