pbi_local_model

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

With no annotations, the description must fully disclose behavior. It explains it reads local files and returns JSON, implying read-only, but does not explicitly state it does not modify anything or discuss error handling, permissions, or side effects.

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 well-structured with bullet points for actions and args. It is concise enough but could be trimmed slightly; however, it remains readable and efficient.

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 few parameters, an output schema exists, and the description covers purpose, usage, and return format. It is complete for a simple file-reading tool, though missing examples or error handling.

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?

The input schema has 0% description coverage, so the description adds the meaning. It explains each action's required arguments (e.g., name required for table/measure) and lists possible action values. This compensates well for the schema gap.

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 reads local PBIP semantic model structure from TMDL files without needing Desktop connection. It lists specific actions (overview, table, measure, etc.) and is distinct from sibling tools like pbi_execute_query which query remote datasets.

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 mentions requirements (pbip_root config) and that no Desktop connection is needed, implying use for offline analysis. However, it does not explicitly compare to alternatives or state when not to use this tool.

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