connect_model

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

With no annotations, the description carries the full burden and does well: it declares read-only behavior, that no model objects are created or changed, and that schemaOnly connections cannot execute queries or live previews. Gaps remain around the lifecycle of a connection (whether it persists, how it is closed) and error behavior when no model is open or the reportDir cannot be resolved.

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 lead sentence is well front-loaded and the mode guidance is compact, but the byPath/byConnection clause is dense jargon (definition.pbir, TMDL, SSAS) that does not correspond to any schema field and reads as internal documentation leaking into the tool description.

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 single nested oneOf parameter with no annotations or output schema, the description covers modes, read-only semantics, the connectionId handoff and the schemaOnly limitation. It could go further on what a successful connection returns and on failure modes, but nothing essential to invoking it correctly is missing.

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, and it mostly does: it explains what the report, desktop and fabric variants each need (reportDir, port, workspaceId/datasetId). However it references 'byPath' and 'byConnection' modes that do not appear anywhere in the input schema, which leaves a dangling concept the agent cannot map to a parameter.

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 first sentence gives a specific verb, resource and scope: 'Connect read-only to an existing model'. It also implicitly positions the tool as the prerequisite for the schema/DAX/preview siblings, so an agent can tell what it is for without opening the schema.

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?

It states an explicit preference order ('Prefer source.kind="report" with reportDir') and then explains when each alternative applies: desktop auto-detects a port, fabric takes workspaceId/datasetId. It also states the downstream usage rule ('Keep connectionId for schema, DAX and previews') and a hard constraint for schemaOnly connections.

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