column_statistics

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

No annotations exist, so the description must disclose side effects or behavioral traits. It states it runs a DAX query but does not explicitly say it's read-only, whether it requires special permissions, or that it may be expensive on large models. This is a significant gap for a tool with zero annotation support.

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?

The description is one succinct sentence (~14 words) that packs the tool's function, specific DAX call, output fields, and scope. Every word adds value; there is no redundancy or 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?

Given no output schema, the description does explain the return concept (per-column metrics), which is useful. However, it fails to mention the required sessionId or the maxRows parameter, and with no annotations it leaves out important context like read-only behavior and potential resource impact. It is adequate but incomplete for a smooth invocation.

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?

The description adds no parameter information. The schema covers only maxRows (50% coverage), and the required sessionId is left unexplained both in schema and description. The description should at least mention that a sessionId is required and what maxRows controls, but it does not.

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?

Description uses a specific verb 'Run' with the exact DAX function EVALUATE COLUMNSTATISTICS() and clearly defines the output scope (per-column Min/Max/Cardinality/MaxLength for the whole model). It distinguishes from sibling tools by emphasizing 'whole model in one call', making its purpose unmistakable.

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 description implies usage when whole-model column profiling is needed ('for the whole model in one call'), but it does not explicitly state when to choose this tool over alternatives, nor does it mention exclusion criteria or when not to use it. This is implied usage rather than clear guidance.

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