get_diagnostic_settings

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

Annotations cover the read-only profile, but the description adds real behavioral context: forbidden/unavailable/unknown states are reported separately, and current switch values are explicitly not proof of historical settings or deleted logs. Only the return/report shape is left implicit.

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 tight sentences, front-loaded with what is read, followed by the evidence caveats and the non-mutation disclaimer. Every sentence carries information; 'forbidden/unavailable/unknown' is slightly compressed but not wasteful.

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 still conveys what the result looks like (switch state plus separately-reported evidence failures) and the critical interpretive caveat. The main gap is the undocumented collection_name parameter, which the description only obliquely covers.

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 50% – collection_name has no description at all, while collectionName carries the alias note. The phrase 'optional table audit metadata' gestures at what the parameter targets, but the description doesn't explain the collection_name/collectionName alias or rejection of conflicting values, so it barely compensates for the gap.

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 and resource: reading current organization trace/audit switches plus optional table audit metadata. It is distinguishable from the audit-history siblings (get_record_audit_history, get_audit_details) by subject matter, though it never names them.

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 negative framing ('Does not enable logging or auditing') plus the warning that current switches don't prove historical settings implies this is a pre-check, not an evidence-gathering step. It never explicitly says when to prefer get_record_audit_history or get_audit_details instead.

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