Compare a target LLM model's costs against a priced baseline using usage records and supplied rates to estimate cost differences; does not change routing.
Compare a target model with known-price baseline. Scenario only; requires quality evaluation and does not change routing.
| Name | Required | Description | Default |
|---|---|---|---|
| rates | Yes | ||
| records | Yes | ||
| targetModel | Yes |
Changes observed during successful MCP inspections.
v0.1.2Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description adds the meaningful behavioral point that this is a simulation/scenario with no routing side effects and that quality evaluation is out of scope, but it never says what the caller gets back or what constraints apply to the comparison.
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 short sentences, front-loaded with the core action and followed by the scope caveat. Nothing is padded, though the second sentence's "requires quality evaluation" phrasing is more confusing than economical.
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 a nested schema at 0% description coverage, a 100k-item array, no output schema, and three mandatory inputs, two sentences are far too thin. The agent cannot tell what shape of records to supply or what the comparison surfaces.
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 0% across three required parameters, one of which is a deeply nested rates object and another a records array of up to 100,000 items. The description only obliquely gestures at targetModel and rates ("known-price baseline"); the records parameter, including inputTokens/outputTokens/cachedInputTokens and requestHash, is completely unaddressed.
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?
"Compare a target model with known-price baseline" gives a verb and a resource, but the object of the comparison is ambiguous: cost? quality? throughput? The mention of "requires quality evaluation" muddies rather than clarifies. Sibling names (estimate_llm_cost, analyze_llm_usage) are never referenced, so the agent must infer the boundary itself.
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?
"Scenario only" and "does not change routing" imply when this tool is appropriate (what-if analysis rather than live actuals), which is genuine usage guidance. However, no alternative is named explicitly, and the agent is left to guess that estimate_llm_cost is the non-scenario counterpart.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.