manage_sensitivity_labels

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

The description adds some behavioral context by mentioning encryption, content marking, and classification policies, which helps clarify the tool's scope beyond what annotations provide. However, it doesn't address important behavioral aspects like the implications of the destructiveHint=true annotation (what gets destroyed), authentication requirements, rate limits, or error handling. No contradiction with annotations exists.

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 a single, efficient sentence that front-loads the core purpose. It avoids unnecessary words and gets straight to the point. However, it could be slightly more structured by separating the different action types or providing a brief example of typical use cases.

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 tool's complexity (8 parameters with nested objects, multiple actions via enum, destructive operations), the description is somewhat incomplete. While annotations provide safety hints and the schema documents parameters well, the description doesn't explain the multi-action nature (list/get/create/update/delete/publish), output format expectations, or error scenarios. The absence of an output schema increases the need for more descriptive context.

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?

With 100% schema description coverage, the input schema comprehensively documents all 8 parameters including their types, descriptions, and constraints. The description adds minimal value by hinting at the settings structure (encryption, content marking) but doesn't provide additional semantic context beyond what's already in the schema. The baseline score of 3 is appropriate given the excellent schema coverage.

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's purpose as managing sensitivity labels for information protection, specifying key functionalities like encryption, content marking, and classification policies. It uses specific verbs ('manage') and resources ('sensitivity labels'), but doesn't explicitly differentiate from sibling tools like 'manage_information_protection_policies' or 'manage_dlp_policies' that might handle related aspects.

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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for choosing specific actions, or how it relates to sibling tools like 'manage_information_protection_policies' or 'manage_dlp_policies' that might overlap in information protection domains.

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