Atomically set properties

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

The description adds behavioral detail beyond annotations by disclosing the rollback mechanism on failure, which is not inferable from readOnlyHint/destructiveHint. It also communicates the 100-property limit, giving the agent a constraint for invocation.

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?

A single well-structured sentence conveys purpose, limit, and atomicity. No redundant information.

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 the key operational detail (atomic rollback) and the invocation limit. However, since there is no output schema, it does not describe the return value or success/failure behavior beyond rollback. Given the destructive nature, mentioning idempotency (already false) is not needed, but confirmation of completion would be helpful.

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 schema already describes clientId as optional with a default, but the 'changes' parameter lacks description. The description clarifies that values are typed, but does not explain the path/property/value structure in detail, leaving some ambiguity for complex use cases.

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?

Clearly states it sets instance properties with a limit of 100, distinguishing it from generic batch operations. The verb 'set' and resource 'instance properties' are specific and align with the tool name.

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 implies usage for setting properties but does not explicitly compare to sibling tools like 'batch' or provide when-not-to-use guidance. The atomic rollback feature is mentioned, giving some context for choosing this tool over alternatives, but it lacks explicit alternatives.

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