Search audit trail

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

With no annotations, the description carries the full load and does it well: it discloses the script-execution authorization requirement and the impersonation failure mode, which an agent cannot infer from the schema. It leaves out result volume/pagination behavior beyond the limit parameter, so it is short of exhaustive.

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 and dense, with purpose and constraints in a single opening clause. The trailing 'When you write to a person...' sentence reads as if lifted from a mutation tool and adds ambiguity rather than clarity, so not every sentence earns its place.

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?

Eight optional parameters and an output schema mean the description only needs to cover intent and operational constraints, which it largely does. The one gap is the unclear closing instruction, which could cause an agent to misuse or misapply it on a purely read operation.

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 100%, so defaults (30 days, limit 20/100) and RFC3339 formats are already documented; the description only restates the filter families. The closing sentence about naming people, roles and requests by display names is oddly phrased for a read tool and does not clearly map to any of the eight filter parameters.

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 ('Query the midPoint audit trail') and enumerates the subject matter (who changed what and when, logins, approvals) plus the filter axes. It is clearly distinguishable from the CRUD/read siblings, though it never contrasts itself with search_objects, the nearest overlapping read tool.

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?

Gives a strong when-not condition: no REST audit endpoint exists in 4.10, so it needs script-execution authorization and fails under resource-server (OIDC) impersonation. It does not name an alternative tool to use when that constraint bites, or say when to prefer search_objects instead.

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