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

With no annotations present, the description carries the full burden, and it does disclose two meaningful traits: the evaluation is deterministic and it returns a weighted score plus row-level issues. It says nothing about auth requirements (workspaceToken), rate limits, error behavior, or whether execution is read-only, which leaves real gaps for an unannotated tool.

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?

Two tight sentences: the capability and scale limit come first, the check list second, the return value last. Every clause carries information and there is 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?

For a five-parameter tool with zero schema descriptions and no output schema, the description omits the most call-critical detail: the format of the `rules` string, which determines whether a call can succeed at all. The return shape is adequately summarized, but parameter-level completeness falls well short of the tool's complexity.

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% across five parameters, yet the description only gestures at two of them: `json` (one object or up to 10,000 records) and `rules` ("data-quality rules"). It never explains the string encoding of the rules payload, what `maxIssues` controls, or what `workspaceToken` and `operationId` are for, so three parameters remain undefined everywhere.

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 and resource ("Run deterministic data-quality rules") and enumerates the exact checks performed (required fields, types, ranges, allowed values, email/URL formats, uniqueness), which clearly separates it from a schema-validator or profiler. It stops short of naming which sibling handles profiling or JSON-Schema validation, so the boundary is inferable rather than stated.

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 scale constraint ("one JSON object or up to 10,000 records") implicitly tells the agent when this tool applies, but there is no explicit when-to-use versus data_quality_profile, json_schema_validate, or data_normalize, and no stated preconditions. Usage is suggested by scope rather than guided.

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