Recallroll

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

Annotations already declare readOnly, idempotent, open-world, non-destructive. The description adds real behavioral context beyond them: it discloses the output ordering (Do Not Drive / Park Outside advisories first) and that remedy plus campaign links are included. It doesn't mention auth or rate limits, but the priority ordering is meaningful added value.

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?

A single front-loaded sentence that leads with the action and scope, then the decoded fields and recall output. Efficient with no filler, though it packs several distinct ideas into one dense clause chain.

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 adequately characterizes returns (decoded attributes plus prioritized recall entries with remedy and link). The main gap is the unexplained 'full' flag, whose effect on the output the agent cannot determine.

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?

The 'vins' param is already documented in the schema, and the description's '1-10' restates maxItems/minItems rather than adding meaning. The boolean 'full' param is undocumented in both schema and description, so half the parameters carry no semantic guidance anywhere.

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 (Decode) plus resource (US VINs) and enumerates the decoded fields (year, make, model, trim, engine, plant) and the recall output. Very clear on what it does, but it never distinguishes itself from the sibling vehicle_recalls, which likely also returns recall data.

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?

Implies usage through scope constraints ('1-10 US VINs') and describes the combined decode+recall workflow, but gives no explicit when-to-use, when-not, or comparison to the sibling vehicle_recalls. The agent must infer the selection criteria.

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

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

Annotations already cover readOnly, idempotent, openWorld and non-destructive, so the safety profile is handled. The description adds genuine non-structured behavior by disclosing result ordering ("advisories first"), which an agent could not infer from the annotations or schema. It stops short of mentioning result volume, rate limits, or the meaning of the `full` flag.

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?

A single sentence with zero filler; the scope (make/model/year, no VIN) is front-loaded and the ordering note is appended efficiently.

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, return-value detail isn't required, and the description covers the lookup inputs and result ordering. The only substantive omission is the unexplained `full` flag, which an agent cannot resolve from schema or description.

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?

make/model/year are self-documenting in the schema (75% coverage) and the description merely restates them. The boolean `full` parameter has no description in the schema and none in the description, leaving a real gap. Baseline 3 is appropriate since the schema carries most of the load.

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 ("List") and resource ("NHTSA safety recalls") scoped by make, model and model year, and distinguishes itself from the sibling check_vins by declaring "no VIN needed" — which is exactly the condition that separates the two tools.

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?

The parenthetical "no VIN needed" gives an implicit selection rule (use this when you lack a VIN), but the alternative check_vins is never named and no explicit when-to-use/when-not-to-use guidance is given. Usage is implied rather than stated.

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