pbi_analyze_model_quality

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

With no annotations, the description carries the full burden. It discloses that the tool 'detects' and 'reviews' specific model elements, suggesting a read-only analysis (since it says 'detecta' and 'revisa'). However, it does not state whether it makes changes, what the output looks like, whether a model must be loaded, or any side effects. It adds some value by listing the checks it performs, but leaves key behavioral traits undisclosed.

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 concise, two sentences long, and each part adds information. The list of checks is dense but valuable, avoiding filler. It is front-loaded with the core purpose (detect model problems) and then elaborates with examples. No waste, though it could have been structured with more clarity around the parameter or usage.

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?

The tool is a quality analysis with multiple checks, but the description does not explain the context: prerequisites, what the output schema provides (though it exists), or how this tool fits with sibling analysis tools. The parameter is unexplained, and there is no mention of whether a model must be open or what 'source' options exist. The list of issues gives some context, but overall completeness is lacking for a tool with one parameter and no annotations.

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 has one parameter 'source' with a default of 'live' and no description. The tool description does not mention the parameter at all, so the agent has no idea what values are valid or what 'source' refers to (e.g., live connection vs. file path). With 0% schema coverage and zero compensation in the description, the parameter is effectively 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 the tool's purpose: detecting typical model quality problems. It lists specific issue categories (measures without folder, long DAX, relationships, calculated columns, visible IDs, missing calendar), giving a concrete sense of what it does. However, it does not explicitly differentiate from sibling tools like pbi_health_check or pbi_audit_model, so it lacks a clear comparative edge.

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 the tool is for detecting model quality issues, but provides no explicit guidance on when to use it versus alternatives like pbi_health_check, pbi_audit_model, or pbi_model_summary. There are no prerequisites, exclusions, or context about the kind of situations where this tool is preferred, leaving the agent to guess.

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