add_report_measure

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

With no annotations, the description carries the burden and does well: it discloses the storage location (layout.config.modelExtensions), calls out the legacy best-known shape with a recommendation to confirm in Desktop, and states the upsert-like behavior (re-adding updates). This is valuable side-effect information beyond a simple 'create' statement.

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?

Three sentences, each adding value: purpose, storage detail, and update semantics. It is front-loaded with the core concept, avoiding filler, and covers essential caveats without being verbose.

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 annotations and no output schema, the description covers the key behavioral aspects: storage location, legacy uncertainty, update behavior, and usage context. It omits error/prerequisite details (e.g., open report session, invalid table), but the combination of schema and description is adequate for a focused creation tool.

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 coverage is high (83%), and the description adds a brief clarification for the table parameter ('host table it attaches to'), but that largely mirrors the schema. It doesn't enrich understanding of daxExpression, formatString, or displayFolder beyond their existing descriptions. Baseline 3 is appropriate when the schema already carries most of the weight.

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 adds a REPORT-LEVEL measure, explicitly contrasting with model measures via 'not the model'. It also names the resource (DAX measure) and host table, making its purpose unambiguous and distinct from siblings like add_measure.

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?

Provides clear usage context: 'handy when you cannot edit the model' indicates when to prefer this tool. It also notes that re-adding the same name updates it, which helps set expectations. No explicit exclusions or alternative tool names are given, but the model-vs-report distinction serves as a strong differentiator.

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