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

Annotations already declare readOnlyHint=true, so the safe-read profile is covered by structured data. Beyond that, the description adds only mode selection and says nothing about result ordering defaults, pagination behavior, or what happens when id and query are both supplied — a concrete ambiguity given the schema allows both. With annotations present the bar is lower, but this still leaves real behavioral questions unanswered.

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?

A single front-loaded sentence with zero filler: the resource comes first, then the branching invocation guidance. Nothing is padded or repeated.

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?

For a six-parameter tool with a nested MongoDB-style query object and no output schema, the description is minimal but serviceable for selecting the tool and mode. The significant gap is that an agent cannot learn from this text what fields exist on a LimAuditLog record, which is exactly what is needed to build a useful query or fields projection.

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% (above the 80% threshold), so the schema itself documents id, skip, sort, limit, and query. The description only restates the id-implied semantics and adds nothing about the undocumented fields parameter or about id/query precedence. Baseline 3 is appropriate since the schema does the heavy lifting.

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?

"Find LimAuditLog records" names a specific verb and resource, and the second clause distinguishes the two retrieval modes (single by id vs. filtered list). It does not explain what an audit-log record contains or how it differs from sibling resources like query_limaccount, but the resource name itself is unique among siblings, so an agent can select it confidently.

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?

It explicitly routes between the two usage modes: pass id for one record, pass query for a filtered list. That is clear context for choosing an invocation shape. It offers no exclusions, prerequisites, or precedence rule for the case where both id and query are supplied.

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