data_check

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

With no annotations, the description must carry the behavioral burden. It usefully discloses that the result is structured as per-check pass/fail plus counts and sample examples, and that all computation is done in code (deterministic, not model-generated). It stops short of confirming the operation is read-only, whether it is expensive to run, or how findings are categorised.

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?

One compact sentence that leads with the operation and immediately describes the return structure, with no filler. The closing clause about code-based computation is short and informative. It is terse to the point of omitting what the seven checks actually are.

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 single-parameter, flat-schema tool with no output schema, the description does enough to sketch the return value. Gaps remain: the seven checks are unnamed, the finding categories are unspecified, and there is no guidance on prerequisites or cost. Adequate but with clear room to be more complete.

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?

There is a single parameter and the schema already documents it fully at 100% coverage, including its provenance from list_runs or build_ontology. The description adds no further meaning about the parameter. The baseline of 3 applies when the schema does the work.

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 operation and its output shape: a data health check reporting pass/fail for seven checks plus per-category finding counts and a few examples. That is far more concrete than a bare name. It does not, however, differentiate itself from the sibling 'health' tool, leaving some ambiguity about which diagnostic to pick.

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?

There is no explicit statement of when to use this tool, when not to, or how it relates to alternatives like 'health', 'run_overview', or 'list_rules'. Usage is only implied by the nature of the operation. The only routing hint, that saved_as comes from list_runs or build_ontology, lives in the schema rather than the description.

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