connect_xmla

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

With no annotations, the description carries the burden and discloses important behavioral traits: it returns a sessionId accepted by downstream tools, defaults come from environment variables, and the token is held in memory only and never echoed. It does not cover session lifecycle or failure modes, but the disclosed security and integration behavior is substantial.

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 front-load the core action and immediately follow with return-value integration, then defaults and security. Every sentence adds unique value with no filler.

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?

For a connection tool with 3 fully documented parameters, no annotations, and no output schema, the description is complete: it explains the return value (sessionId), downstream compatibility, service-versus-local context, environment defaults, and security handling. Nothing critical is missing for correct selection and invocation.

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%, so the schema already fully documents catalog, endpoint, and accessToken. The description adds no true parameter-level meaning beyond the schema except reinforcing the environment-variable defaults and the token-in-memory behavior, which is only tangential to parameter semantics.

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 uses a specific verb ('Connect') and resource ('Fabric/Premium XMLA endpoint') and clearly distinguishes itself from local Power BI Desktop usage. The powerbi:// example and the explicit contrast with 'instead of local Power BI Desktop' leave no ambiguity about what this tool does.

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 clearly indicates when to use it (before session-based tools such as run_dax, validate_dax, export_tmdl, run_bpa) and that it targets service endpoints instead of local Desktop. It does not explicitly name alternative tools like connect_model in a when-not-to-use sense, so it stops short of a 5.

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