find_deals

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does well: it reveals that the tool ranks listings, that each item carries reasons/risks/risk_flags/project_score, and that sort_by='project' requires a profile. It also implies the tool scores listings rather than just filtering them. However, it does not disclose details like whether the tool mutates anything (it doesn't appear to), rate limits, or what the output schema contains beyond the listed fields. The description adds meaningful behavioral context beyond the schema, but stops short of full transparency.

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 description is two sentences, front-loaded with the core purpose ('Rank listings by deal signals and/or project-car score') and the key signals. The second sentence gives a concrete usage example. Every clause earns its place; there is no filler or repetition of schema details. It is appropriately sized for a tool with 19 parameters.

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?

Given the tool's complexity (19 parameters, scoring logic, output schema), the description is reasonably complete: it explains the scoring dimensions, the output fields, and the project-car use case. The output schema exists, so return values need not be fully described. However, it does not explain the meaning of 'deal' vs 'combined' sort modes beyond the sort_by parameter description, nor does it clarify how the profile dict fields (budget, likes, etc.) affect scoring. These are gaps an agent might need to fill by inspecting the schema or making trial calls.

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 47%, so the description must compensate for the many parameters without descriptions (make, model, year_min, year_max, price_min, price_max, seller_type, transmission, keywords, etc.). The description does add value by explaining the scoring semantics: it names the deal signals and the project_score, and it clarifies how sort_by and profile interact. However, it does not explain the meaning of many filter parameters (e.g., what seller_type values are valid, how keywords interact with scoring). The description partially compensates for the coverage gap but leaves several parameters semantically under-specified.

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 states a specific verb ('Rank listings') and a clear resource ('deal signals and/or project-car score'), and enumerates the exact signals used (comps position, price drops, time on market, seller, description risk flags). It also names the output fields (reasons, risks, risk_flags, project_score), which distinguishes it from sibling search tools like search_cars or find_price_drops. The explicit mention of 'best project cars' usage further clarifies its unique role.

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 description gives a concrete usage directive: 'Use sort_by='project' + a profile to answer 'best project cars'.' This tells the agent when to use this tool for a specific intent. However, it does not explicitly state when NOT to use it or name alternatives like find_price_drops or find_long_sitting_listings, which are siblings that might overlap. The guidance is clear for the project-car case but lacks explicit exclusions for other deal-finding scenarios.

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