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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds one genuine behavioral constraint — simulated items are 'Caliper-run evals only' — but says nothing about the notable approvalId/needs_confirmation flow this mutation triggers, leaving a real gap for a write tool.

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?

Front-loaded with the core purpose and 'first step' positioning, then structured into the three item shapes. It is long, and phrases like the message-ten anecdote and the Compass-source advice are more persuasive than operational, but most content earns its place for a complex nested schema.

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?

For a 6-parameter tool with a nested items array and no output schema, the description covers the item taxonomy thoroughly and explains how each shape is used in evals. The main omission is any mention of the approval/confirmation handshake that the approvalId parameter implies.

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%, so the baseline is 3, but the description goes beyond it by organizing the nested item parameters into three named shapes (Q&A / SEQUENCE / SIMULATED) and clarifying the role of fields like disposition, expectedResponse, and expectedBehavior. This adds conceptual meaning over the flat per-field schema 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?

States a specific verb+resource ('Creates a dataset of test items') and explicitly positions it as 'THE FIRST STEP of setting up evaluation for a flow', which cleanly separates it from siblings like caliper_datasets_add_items and caliper_datasets_update. An agent knows exactly what this does and where it sits in the workflow.

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?

Gives clear context ('first step' of eval setup) and prescriptive guidance on when to use sequence/simulated items versus Q&A, plus where to source realistic inputs (Compass pages). It does not explicitly name the alternative sibling for appending items to an existing dataset, so routing is implied rather than spelled out.

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