query_audit_events

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

Annotations only declare readOnlyHint=true; the description goes well beyond that by disclosing the exact return payload (events, count, returned, limit, truncated, scanTruncated) and the non-obvious semantics of truncated/scanTruncated, plus a strong inference rule against characterising the trail from a truncated result. It omits auth requirements, rate limits, or default page size.

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?

Front-loaded one-line purpose, then a compact args block and a returns block; every line carries information given the 0% schema coverage. The Args list is slightly list-heavy but justifiable since the schema documents nothing.

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 and ten undocumented parameters, the description compensates fully: it documents every filter, explains the return envelope, and warns about the truncated/null-truncated edge case that would otherwise cause a wrong conclusion. Nothing an agent needs to call and interpret this correctly is missing.

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 0%, so the description carries the full burden and does so: it defines source, skill/tool/status/risk_level as field filters, approved as a boolean approver-presence filter, selector as an evidence-class selector with enumerated values, since/until as ISO bounds, and limit as row cap. All ten parameters get meaning not present in the bare JSON schema.

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 ('Cross-tool audit event query') and signals primacy with 'the workhorse', so an agent knows this is the general-purpose event query. It stops short of explicitly differentiating from siblings like activity_timeline, approval_report, or exceptions_report, which overlap in domain.

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?

Usage is implied rather than stated: 'the workhorse' suggests default choice, and the truncation caveat tells the agent when a result is not trustworthy as a final count. There is no explicit when-to-use-this-vs-alternative guidance naming a sibling or a condition that routes elsewhere.

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