pbi_create_measure

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: validation of table/measure existence, the overwrite behavior, the data_category rendering context, the mode restriction ('both' disabled), and that it returns a diff. This is substantive, though it omits details like permission requirements and error handling specifics.

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 a single paragraph with a clear opening statement about the core action, followed by validation behavior, an optional parameter example, a note about return value, and a mode restriction warning. It is moderately concise and front-loaded, though the mode='both' explanation adds length but earns its place.

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 (10 parameters, no annotations, 0% schema coverage), the description covers the main purpose and a few key parameters but leaves many parameters unexplained. The existence of an output schema somewhat mitigates the need to describe return values, but the incomplete parameter documentation limits contextual completeness.

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%, so the description must compensate for all 10 parameters. It only explains data_category (with an example) and mode (with the live/pbip/both distinction), and partially implies overwrite semantics. The other seven parameters (table, name, expression, description, format_string, display_folder, request_id) are left undocumented in both the schema and description, leaving a significant gap.

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 creates or replaces (with overwrite=true) a DAX measure, using the specific verb 'crea' and the resource 'medida DAX'. It distinguishes itself from sibling tools like pbi_update_measure and pbi_delete_measure by focusing on creation/replacement.

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: it validates that the table exists and that the measure doesn't already exist unless overwrite is true. It also gives explicit guidance on the mode parameter, explaining that 'both' is disabled and advising to choose 'live' or 'pbip'. However, it does not explicitly exclude alternatives like pbi_update_measure when modifying an existing measure.

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