pbi_diagnose_data

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

The description goes well beyond the annotations by explaining deterministic behavior, absence of heuristics, how skipped checks are reported, severity assignment for critical fields, and the requirement for a live open model. This adds substantial context not available from the readOnlyHint and openWorldHint annotations.

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 dense yet well-structured, starting with a clear purpose statement followed by a bulleted list of checks, then behavioral notes and prerequisites. Every sentence contributes value, with no redundant or filler content, and the front-loaded opening ensures quick comprehension.

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 the tool's complexity (four checks, skipped states, severity rules, prerequisites), the description is remarkably complete. It explains what each check does, how failures are categorized, the deterministic vs. subjective split, the skipped status semantics, and the model-open requirement. The output schema exists, so return values need not be described.

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 schema provides no descriptions for the two parameters (0% coverage), so the description must compensate. It explains the `tables` parameter's filtering semantics effectively ('narrows to relationships that touch those tables'), but it does not mention `request_id` at all. Thus, the compensation is partial, leaving one parameter completely unexplained.

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 clearly states a specific verb ('diagnose') and resource (data content against the live model), and enumerates the four deterministic checks. It distinguishes itself from metadata-only audit tools by explicitly targeting what 'breaks dashboards and no metadata sees', making it unique among siblings.

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 provides clear context for when to use this tool: to find data-level issues invisible to metadata, and it notes the prerequisite of an open model in Desktop. However, it does not explicitly contrast with alternatives like pbi_profile_data or pbi_analyze_model_quality, nor does it state when not to use it, stopping short of the 'explicit alternatives' benchmark.

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