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

With no annotations, the description carries the full burden and does substantial work: it defines what 'reviewed', 'raw', and 'none' mean, tells the agent to cite reviewed analysis, instructs it to surface rawTopComponents on unreviewed data, and forbids fabricating issues. It omits auth requirements, but for a read-only vehicle lookup that is a minor 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?

The trigger is front-loaded, followed by compact mode-by-mode handling and a closing guardrail ('Never invent issues') — every sentence drives agent behavior. The telegraphic style ('is Wrench.Pro's human-reviewed analysis') is dense but not padded.

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?

An output schema exists, so return shapes need not be spelled out, and the description instead supplies the interpretation rules an agent needs for each mode plus an anti-hallucination instruction. What is missing is only the relationship to sibling tools like get_recalls, which would help an agent disambiguate reliability vs. safety-recall queries.

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 all three required parameters (year, make, model) are documented with resolve_vehicle provenance, so the schema already does the heavy lifting. The description adds no syntax or format detail for these inputs; the mode values it discusses appear to be response fields rather than input parameters, which is baseline-3 territory.

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 is framed as a trigger ('Use when the user asks what commonly goes wrong, about reliability, or about a specific symptom'), which implies the resource is known-issue/complaint data, and the mode semantics make clear what is returned. It stops short of explicitly stating the verb+resource ('returns known issues for a vehicle') and never names get_recalls as the sibling it is not, so an agent must infer the boundary from the domain wording.

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?

It gives a concrete when-to-use trigger covering reliability questions and symptom questions, and prescribes handling for each mode ('reviewed' = cite it; 'raw' = say no reviewed issues and present rawTopComponents; 'none' = say no complaint data). There is no explicit when-not or alternative-tool routing, which keeps it out of 5 territory.

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