apply_rename_plan

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

With no annotations provided, the description carries full responsibility for behavioral disclosure, and it excels: it details skip-with-reason behavior, atomic batch execution, single SaveChanges, DAX/M reference rewriting, conditional report binding rewriting, and the result row format. This gives the agent a thorough understanding of side effects and guarantees.

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 dense but well-structured: it starts with the core action, then details the input format, error handling, atomicity, optional reportSource behavior, and output. Every sentence contributes meaningful information without redundancy, making it efficient for an agent to parse.

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 description covers most critical aspects: input format, validation behavior, atomic execution, optional report rewriting, and result row count. It lacks explicit mention of prerequisites (e.g., open session) or permission requirements, but given the complexity and presence of sessionId, the description is sufficiently complete for tool 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 description coverage is 67% (planJson and reportSource described, sessionId not). The description adds significant value by specifying the exact accepted formats for planJson (audit_naming's renamePlan object or bare array) and the possible types for reportSource (reportSessionId, pbirSessionId, PBIR path). This goes beyond the schema's basic descriptions.

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 the specific verb 'APPLY' with a clear resource ('audit_naming rename plan') and differentiates itself from sibling rename tools by focusing on a pre-generated plan and propagating rename machinery. It clearly identifies the tool's purpose without ambiguity.

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 explicitly ties the tool to audit_naming's renamePlan, indicating when it should be used (to apply a batch rename plan). It does not explicitly mention alternatives or exclusions, but the context strongly implies it is for complex, multi-object renames that need atomic execution and reference rewriting.

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