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

Annotations already cover the safety profile (read-only, idempotent, non-destructive), so the bar is lower. The description still adds real context beyond them: the lookup runs in reverse (sign to cause), results are organized per engine, and it explicitly disclaims diagnosis. It does not say how matching is performed or how results are ranked, which keeps it from a 5.

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 input scenario and its examples. The second sentence partly restates the first ('list the documented failure modes' vs 'Lists documented causes'), which is mild redundancy rather than bloat.

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 two-parameter, no-output-schema tool the description is nearly sufficient: it says what comes back (documented failure modes, per engine). The notable gap is that symptom is a free-form string with no enum, and the description never says whether matching is exact, keyword-based, or fuzzy, which materially affects how an agent should phrase the call.

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 coverage is 100%, so both parameters are already documented, and the baseline is 3. The description does extend the symptom vocabulary beyond the schema's examples and implies that platform narrows to one engine, but adds no format or matching rules for the free-form symptom string.

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 concrete verb and resource: given a symptom, list documented failure modes that present that sign, grouped per engine. The examples (hard start, power loss, white smoke, coolant loss, DEF warnings) make the input domain unmistakable. It does not explicitly distinguish itself from the sibling get_failure_modes, so it falls short of 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?

Usage is implied rather than stated: the symptom-first framing tells an agent to reach for this when it starts from an observed sign. The exclusion 'it does not diagnose a truck' usefully bounds expectations, but there is no explicit guidance on when to prefer get_failure_modes or get_repair_cost instead.

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