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

readOnlyHint=true already tells the agent this is a safe read, and the description adds only the mode split. It omits behavior an agent needs in practice: that results are paginated by default at 50, that out-of-range limits are silently clamped, and that sort supports a '-' descending prefix.

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 the primary behavior first and the mode split second. Nothing is wasted and nothing is buried.

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 filter object and no output schema, the description covers only the top-level mode choice. It leaves pagination defaults and result shape to the schema, which is workable given 83% coverage but not fully self-sufficient.

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 83%, so the schema already documents id, skip, sort, limit, and query with examples and clamping rules. The description restates the id-versus-query distinction but adds no syntax or constraint detail beyond the schema, so the baseline 3 applies.

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 names a specific verb ('Find') and resource ('LimSave records'), and it distinguishes the two operating modes: single record by id versus a filtered list via query. It does not reference any sibling, but with ~100 same-shaped query_lim* siblings the entity name alone is the differentiator.

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 gives an implied selection rule ('pass id for one record, or query for a filtered list'), which is enough to choose a mode. It does not state when to prefer this tool over a dedicated search/filter sibling, nor does it warn about broad unbounded queries.

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