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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, yet the description adds real value beyond them: cost ('Free'), the returned confidence tiers, alternative candidates, and a specific mismatch warning that params.year may differ from the requested year (extracted.year). The human-in-the-loop instruction for ambiguous resolutions is exactly the behavioral context annotations cannot carry.

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?

Front-loads the key qualifier ('Free') and the primary use case, then flows into outputs, downstream wiring, and edge-case handling. Several clauses are dense and run together, but no sentence is filler — the only cost is readability, not waste.

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 one-parameter resolver with an output schema, this covers everything an agent needs: when to call it, what it returns (confidence, candidates), how to consume vehicle_id downstream, and how to handle ambiguity or a year mismatch. Nothing material is left to inference.

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 single query parameter is already 100% documented in the schema, so the schema does the heavy lifting. The description still adds meaning by specifying which fields the free text should contain (year, make, model, view, color when named) and clarifying that make/model are parsed with the same rules the image tools use, which tells the agent why the phrasing matters.

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 transformation: turn a free-text request into the catalog vehicle plus exact get_car_image parameters, and enumerates those parameters (vehicle_id, make, model, year, view, color). The worked example ('red 2018 Mazda MX-5 Miata side view') makes it unmistakable against siblings like search_vehicles or list_image_options.

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?

Explicitly positions itself as 'the first call for any picture of a car, including one you chose yourself,' which is clear when-to-use routing, and names the downstream consumers (get_car_image, create_car_image_urls, create_3d_model). It also gives an escalation rule for low confidence or multiple candidates, but never states when to prefer search_vehicles or list_image_options instead, so the alternative-space is only partially covered.

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