connect_target

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

No annotations are provided, so the description carries the full behavioral burden. It discloses auth modes (interactive browser login vs service_principal) and that the result carries session_id, engines_available, and diagnostic warnings, which is useful. It is silent on session lifecycle: whether repeated calls create duplicate sessions, whether a session must be closed, what happens on connection failure, or whether the call is stateful/side-effecting — significant gaps for a session-initializing tool with zero annotation coverage.

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?

Front-loaded with the action and effect, then organized into use-when, Args, and Returns, so a scanning agent finds routing information first. Efficient overall, though the Returns block restates what the output schema already delivers and could be trimmed.

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 4-parameter tool with an output schema present, the description covers every argument's meaning, the conditional requirement, the default, and the high-level result shape. The remaining omission is session lifecycle/cleanup behavior, which matters for a stateful connect call but is not fatal given a documented return type.

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 does: it enumerates the valid target_type values, explains that target_ref is a path for PBIP/PBIX but a workspace UUID for Fabric, states the auth_mode default ('interactive', browser login), and adds the conditional requirement that tenant_id is needed when auth_mode is service_principal. This adds semantics the schema does not carry.

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?

States a specific verb+resource (connect to a Power BI target) plus the secondary effect (initialize an orchestrator session), which distinguishes it from the pipeline/modification siblings that all assume a live session. The target_type enumeration ('pbi_desktop', 'fabric_workspace', 'pbip_folder', 'pbix_file') further pins down scope. An agent can identify this as the session bootstrap step 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?

Provides an explicit 'Use this tool when the user asks to...' block covering both the connection request and the intent to start an interactive inspection/modification session. However, it names no alternatives or exclusions — it never says whether this must precede plan_change/apply_plan or how it relates to powerbi_health. Clear context, but no routing away from siblings.

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