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

With no annotations provided, the description carries the full behavioral burden. It usefully discloses the return contents (total cost, per-run cost, parallel time estimate) and the sample/model/trial inputs, but says nothing about side effects, determinism, or whether it is a pure local calculation versus a billable API call.

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 tight sentences: the usage trigger is front-loaded, followed by a compact statement of inputs and outputs. No filler or restated name.

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?

Although there is no output schema, the description enumerates the three return values, and all 10 parameters are documented in the schema. For a stateless calculator this is nearly complete; only cost-model assumptions (provider pricing, judge pass effects) are left implicit.

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 description coverage is 100% and every parameter has a documented default, so the schema already does the heavy lifting. The description only echoes 'samples/models/trials' and adds no syntax, units, or interaction details beyond that baseline.

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 gives a specific verb+resource ('budget an LLM evaluation run') and the domain term 'eval' inherently separates it from sibling calculators like fine-tune-roi-calculator or rag-pipeline-cost-calculator. It stops short of explicitly naming which sibling to use instead, so it does not reach a 5.

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?

'Use when a user needs to budget an LLM evaluation run' is a clear trigger condition that tells the agent the right context. There is no guidance on when NOT to use it or which of the many sibling cost calculators to prefer, so it misses the exclusions a 5 would require.

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