Car Listing Check

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

Beyond readOnlyHint/idempotentHint/destructiveHint/openWorldHint, the description discloses that nothing is fetched or scraped, images are never inspected, facts are never verified, output is always English while German and English keywords are understood, nothing is stored or changed, and operational call metrics are logged. The logging disclosure and the 'recommendations are not portal limits or legal advice' caveat are exactly the kind of 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?

Purpose and trigger are front-loaded in the first sentence and the dense single block is efficient. There is measurable redundancy: media is disclaimed three times ('does not inspect images', 'no media generation', 'No images or videos are generated') and 'legal advice' appears twice, which could be consolidated into the single exclusion list.

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 10-parameter tool with a nested 30-field object, an output schema and full annotations, the description covers scope, non-capabilities, language resolution and side effects (metrics logging) well. The remaining gap is the relationship to the sibling checklist tool, which a user-facing agent will plausibly hesitate between.

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 the nested `fields` object documents all 30 sub-properties inline, so the schema carries the semantic load. The description only restates limits already present (title 300, description 20,000, up to 100 photo URLs or a count) and echoes the title-or-description requirement that the anyOf already encodes. This is the baseline case where the schema does the work.

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 opening sentence gives a specific trigger condition plus a concrete output set: 'best-practice score, missing data and prioritised fixes' for a 'dealer vehicle listing'. That is far more than a restatement of the name. It stops short of a 5 because it never names the sibling get_car_listing_checklist, so an agent must infer the boundary between 'check' and 'get checklist' from the exclusion list rather than from an explicit contrast.

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 stated positively ('when the user supplies a dealer vehicle listing and wants a best-practice score') and negatively with five enumerated non-uses: retrieving listings, valuations, vehicle inspections, media generation and legal advice. An agent can decide to call or not call without opening the schema. The only softness is that excluded tasks are redirected nowhere by name.

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 declare readOnly, idempotent, non-destructive and closed-world, and the description adds substantive context on top: no scraping, no fact verification, not legal advice, no media generated, no listing stored or changed, and operational call metrics are logged. That last detail is a genuinely useful disclosure an agent could not get from the annotations.

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 condition and return contents are front-loaded, and the exclusion list is compact. There is mild redundancy between 'does not fetch or scrape any website' and the later 'Do not use for ... retrieving ads', which could be consolidated without losing meaning.

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, read-only, idempotent lookup tool with an output schema, the description covers everything an agent needs: what it returns, what it will not do, and the boundary against live-checking siblings. Return value details can be left to the output schema, so nothing material is missing.

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 both parameters are enums with their own descriptions, so the schema already carries the semantics. The description only restates that market and condition are optional filters ('optionally for a new or used vehicle'), adding no format or defaulting detail beyond what the schema supplies.

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 names a specific verb+resource ('static dealer vehicle-listing checklist') and scopes it by market (Germany, US, UK, generic) and condition, then enumerates the returned artifacts: recommended fields, photo order, title pattern and description structure. This is clearly separable from the sibling check_car_listing, since the text explicitly rules out live portal rule checking and ad retrieval.

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 opens with a clear triggering condition ('Use this when the user wants...') and closes with an explicit when-not list (live portal rules, retrieving ads, inspections, image/video generation). The only gap is that the alternative tool is described by function rather than named, so the agent must infer that check_car_listing is the intended destination for live-rule checks.

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