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

The description adds useful behavior beyond the readOnlyHint annotation by stating that the call costs 0 credits and that the returned estimate is computed by the same functions that actually charge analyses_run. This reassures the agent that the estimate is accurate and side-effect-free. No annotation contradiction 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?

Two sentences, no filler. The most important trait (costs 0 credits) is front-loaded, followed immediately by what the tool returns and how the estimate is computed. Every sentence earns its place.

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 tool with one simple parameter, no output schema, and read-only/open-world annotations, the description covers what the agent needs: cost, return value, relationship to analyses_run, and accuracy guarantee. No critical information is missing.

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%: itemCount is documented as 'How many items you would send' with min and max values. The description's phrase 'that many items' reinforces the parameter's meaning but does not add substantial new semantics beyond the schema, so the 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 states a precise verb (returns) and resource (how many credits analyses_run would charge), and clarifies scope ('for that many items, per kind'). It clearly differentiates this from analyses_run by framing it as a zero-credit estimation tool, leaving no doubt about what the tool does.

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 implicitly tells the agent when to use this tool: instead of running analyses_run, call this to learn the credit cost in advance. It names analyses_run as the relevant alternative. It does not explicitly mention excluding query_estimate or explore_estimate, but the reference to analyses_run is sufficient for the primary use case.

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