Set Annotations

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

The description richly discloses non-idempotency, partial mutation semantics, possible false failures, and validation steps, going far beyond the openWorldHint annotation. This is exemplary behavioral transparency.

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?

Two dense sentences convey the core purpose and critical operational warnings without filler. Every clause adds value, and the warning about non-idempotency is essential to safe use.

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 batch, non-idempotent nature and the presence of an output schema, the description covers operational pitfalls, error handling, and verification workflow. It is complete enough without explaining return values.

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 coverage is 100% with detailed descriptions for the annotations array, including the properties enum and nodeName requirement. The description itself adds no additional parameter-level meaning, so the baseline of 3 applies.

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 states 'Append native annotations to one or more nodes in a batched call' – a specific verb and resource. It clearly distinguishes from sibling annotation_list and other node-related tools.

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?

It provides actionable guidance on handling partial_success and explicitly instructs to call annotation_list before retrying non-success items to avoid duplicates. However, it does not broadly state when to use this tool vs alternatives beyond this retry scenario.

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