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

Annotations already declare the tool read-only and idempotent, so the description does not need to restate that. It adds valuable behavioral context by specifying the output format (ranked results with Ψ scores and state classification) and the mutual exclusivity requirement, which goes beyond the annotations and enriches the agent's understanding of the tool's behavior.

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 two sentences: the first covers purpose and output, the second gives a clear directive. Every word earns its place; no redundant filler or irrelevant detail.

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 5-parameter tool with good schema coverage and safety annotations, the description sufficiently communicates the key behaviors (return format, mutual exclusivity). It does not explain pagination details, but those are in the schema. The absence of an output schema is compensated by mentioning the output fields, making the description complete enough for 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 coverage is 100% with each parameter described. The description repeats the 'exactly one' constraint but does not add additional meaning beyond the schema's own descriptions (e.g., 'mutually exclusive with collection'). Since the schema already carries the load, a baseline of 3 is appropriate.

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 identifies the action ('Search a ColdState index'), the target resource (by collection name or index ID), and the return type (ranked results with Ψ scores and state classification). This distinguishes it from siblings like coldstate_search_global and coldstate_batch_search, which imply different scopes or modes.

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 a clear constraint ('Provide exactly one of `collection` or `index_id`') but does not explicitly state when to use this tool versus alternatives, nor does it mention exclusions. The usage context is implied by the tool name and description, but there is no explicit guidance on tool selection.

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