audit_search

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

No annotations are provided, so the description carries the full burden. It adds meaningful behavioral context by mentioning the structured audit log, redacted JSON lines, and specific event types like tool_denied and tool_window_denied. Still, it does not clearly state whether the operation is read-only, whether special permissions are needed, or how results are ordered.

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?

The description is front-loaded with purpose, uses concrete answerable questions to establish scope, and then presents a tight, scannable argument list. Every line earns its place with no filler.

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?

All seven optional parameters are explained, the output schema covers return values, and examples make invocation straightforward. The main gaps are lack of sibling differentiation from audit_recent and no mention of default behavior when no filters are supplied, but overall this is sufficient for correct calling.

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%, and the description fully compensates by documenting all seven parameters with useful semantics: tool name/prefix examples, agent ID source, event types, substring query behavior, inclusive ISO timestamps, and the 1–200 limit range. This is far beyond what the bare input schema provides.

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 clearly states the tool searches the structured MCP audit log and lists concrete questions it answers, such as which agent restarted which service or whether a call was denied by policy. It does not explicitly contrast itself with the similar sibling tool audit_recent, so it slightly misses the sibling-differentiation bar for a 5.

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 'Answers: ...' list implies when this tool is useful, such as investigating who triggered an update or why a call was denied. However, there is no explicit guidance about when to choose audit_search over audit_recent or other auditing tools, and no exclusion criteria.

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