save_pbir

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

With no annotations provided, the description carries full responsibility and does so exceptionally well. It discloses specific behaviors: only changed files are re-emitted, every other entry is preserved byte-for-byte, GUID names remain intact, the DataModel is untouched, SecurityBindings are stripped, and it clarifies zip repacking vs PBIP folder writes. It also flags the prerequisite about Power BI Desktop, covering critical side-effect conditions.

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 two sentences long, densely packed with critical details, and front-loads the primary action. Every clause contributes meaning—from the selective re-emission to the format-specific handling and the prerequisite—with no 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?

Given the single parameter and lack of output schema/annotations, the description covers the tool's main behavior thoroughly, including format differences and constraints. However, it does not mention what the tool returns or success/failure indicators, which would be useful in the absence of an output schema.

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, but it does not explicitly explain the `pbirSessionId` parameter. While the parameter name and tool context suggest it is the session identifier for the open PBIR report, the description adds no direct guidance on how to obtain or use it, leaving a gap for the agent.

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 action ('Persist the open PBIR report') with a specific resource, and distinguishes it from sibling tools like save_report or persist_open_model by detailing exact behaviors (e.g., re-emitting only changed files, stripping SecurityBindings). It also clarifies format-specific handling for .pbix vs PBIP, making the purpose unmistakable.

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 provides clear context for when to use the tool (to persist changes to an open PBIR report) and includes an important prerequisite (the source must NOT be open in Power BI Desktop). However, it does not explicitly name alternatives or when-not-to-use compared to sibling tools, so it falls short of full differentiation guidance.

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