Compare ads

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds meaningful behavior beyond that: it discloses the computed outputs (cheapest, cheapest_saves_pct, compared_by), the per-metre normalization rule when all priced ads have an area, and the fact that identical specs are collapsed. That is substantive disclosure of what the tool computes and returns.

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?

It is dense but front-loaded: the core comparison semantics come first, then the computed fields. Every clause conveys distinct information about output shape; the parentheticals are slightly heavy but not redundant.

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?

There is no output schema, so the description carries the burden of describing results, and it does so thoroughly (cheapest, savings percentage, differing rows, shared specs, unique features, compared_by). The only gap is the absence of routing guidance to sibling tools, which is a usage rather than completeness concern.

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% and the single 'tokens' parameter is fully described there (2–6 ad tokens). The description adds nothing about token format or provenance, but with complete schema documentation the baseline of 3 is appropriate.

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 opens with a specific verb and resource ('Side by side: the price of each ad') and immediately scopes the output ('only the specs that differ'). It is clearly distinguishable from siblings like dv_cheapest, dv_appraise, and dv_similar, which perform different single-ad or ranking operations.

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 states a real constraint — 'Works across ads of the same kind (two cars, two flats)' — which tells the agent when the tool is applicable. However, it never names an alternative (e.g. dv_cheapest, dv_appraise, dv_similar) or explains when to prefer comparison over those tools, so the when-to-use guidance is only implied.

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