score_dealGrade a car deal: compare asking price to expected market value. ZIP is optional. Same inputs/outputs as POST /api/score.
| Name | Required | Description | Default |
|---|---|---|---|
| vin | No | ||
| zip | No | ||
| make | No | ||
| trim | No | ||
| year | No | ||
| model | No | ||
| mileage | Yes | ||
| asking_price | Yes |
Changes observed during successful MCP inspections.
Input schema / requiredPrevious value: -[
- "asking_price",
- "mileage",
- "zip"
-]New value: +[
+ "asking_price",
+ "mileage"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden but does not say what the output looks like (a letter, a numeric score, a range?), whether it is deterministic, or what errors can occur. 'Same inputs/outputs as POST /api/score' references an external REST endpoint the agent cannot inspect, which adds no usable behavioral detail.
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?
Three short sentences with the core purpose front-loaded and no filler prose. The final API-endpoint sentence is of questionable value to an MCP agent, but the text is otherwise tight and well-ordered.
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 an 8-parameter tool with no annotations, no output schema, and 0% schema coverage, the description leaves too much unsaid: the meaning of a 'grade', how the market-value comparison is expressed, and the semantics of the six undocumented inputs. It is adequate only at the highest level of the operation.
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 8 parameters, so the description must compensate and mostly does not: required 'mileage' is never mentioned, and vin/make/model/trim/year are left entirely undocumented. The one statement given ('ZIP is optional') merely restates that zip is absent from the required list, adding no new meaning.
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 ('Grade a car deal') and immediately explains the operation: 'compare asking price to expected market value.' This is far clearer than the bare name, though it never distinguishes itself from the sibling 'explain_grade', leaving the boundary between scoring and explaining implicit.
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?
There is no explicit guidance on when to call this versus 'explain_grade' or what a valid call requires. 'ZIP is optional' is the only usage-style hint, and it is a parameter note rather than a routing instruction. An agent must guess the scenario boundary between the two grade-related siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.