eval_dax_offline

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It openly states that the tool briefly opens the file in Power BI Desktop (a window appears), runs the query, then closes Desktop, and explains how bare table expressions are handled. It does not explicitly state that the file remains unmodified, but the context implies a read-only evaluation.

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 three sentences, each contributing useful information: what it does, the side effect (Desktop window), and how input differs from an alternative. It is front-loaded with the core purpose and avoids any redundancy or fluff.

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 has no output schema, but the description tells the result shape (columns + rows). It also covers the execution lifecycle (open, run, close), the accepted input forms, and how it differs from `run_dax`. It could mention error behaviors or timeout details, but the essential information for correct invocation is present.

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 100%, giving a baseline of 3. The description adds extra meaning by clarifying that `dax` may be a full EVALUATE query or a bare table expression (EVALUATE is prepended) and that `pbixPath` must point to a CLOSED .pbix. This goes beyond the plain parameter descriptions in the schema.

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 starts with a specific verb ('Evaluate') and resource ('DAX query against a CLOSED .pbix'), and clearly states the output shape (columns + rows). It also distinguishes itself from the sibling tool `run_dax` by noting the same result shape but no session and no manually-open Desktop, which unambiguously differentiates it.

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 implicitly provides usage guidance by contrasting with `run_dax` ('Same result shape as run_dax, but no session / no manually-open Desktop'). This tells an agent when to choose this tool (closed file, no existing session) without explicitly stating 'use when X, use run_dax when Y'. It also warns that a Desktop window appears, which is a side-effect to consider.

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