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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds value the annotations cannot: it enumerates the return shape (total cost, per-run cost, parallel time estimate), which matters because there is no output schema. It does not disclose the pricing assumptions or data source behind the estimate, which is the remaining gap.

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, zero filler, and the usage condition is front-loaded ahead of the output summary. Nothing repeats the name or title verbatim.

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?

With no output schema, the description's mention of the three returned values is genuinely load-bearing, and the schema fully covers inputs. Minor gap: it never says how costs are derived (pricing table, assumption of defaults), which matters for a budgeting tool whose accuracy depends on those assumptions.

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% with 10 documented parameters, including defaults for model, tokens, judge settings, and trials. The description only gestures at samples/models/trials without adding syntax or units beyond the schema, so the baseline 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?

States a specific verb+resource (calculate the cost of an LLM evaluation run) and scopes it tightly enough to separate it from siblings like rag-pipeline-cost-calculator and agent-loop-cost-calculator. It even names the outputs (total cost, per-run cost, parallel time estimate), so the agent knows exactly what comes back.

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" gives a clear triggering condition, which is more than most siblings offer. It stops short of naming alternatives (e.g., 'use provider-cost-calculator for raw token pricing'), so no exclusion guidance is present.

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