Verify Compared Offer

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

Although annotations already declare the tool read-only, idempotent, and non-destructive, the description adds substantial behavioral context: it returns a source card that preserves fields which comparison normalises away, it reports live deltas, and it specifies both the error taxonomy (BadRequestError for invalid source/ID and native source errors). This goes meaningfully beyond the structured 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 description is front-loaded with a concise single purpose sentence and then fleshed out with clearly separated Return Format and Error Format sections. Each sentence adds useful context; slightly more verbose than strictly necessary, but all content is substantive.

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 an output schema present, the description reasonably limits itself to Return Format and Error Format, which together give a full overview of what the tool returns and what fails. It is a little thin on how expected_price_rub affects behaviour, but the schema fill that gap, and overall it is sufficient for an agent to call the tool correctly.

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%, so the baseline is 3. The description reinforces that source and product_id come from a compared offer and that expected_price_rub is used for a delta, but it mostly repeats what the schema already states. No direct parameter-level elaboration is added in the description text.

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 ('verify'), a specific resource ('a parsed offer'), and the mechanism ('through its marketplace card tool'). It also distinguishes the tool from richer siblings by positioning it as the cheap follow-up that avoids the 36-tool unified mount, making its role clear even without inspecting sibling schemas.

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 clear context for use ('following compare_prices', 'without enabling the 36-tool unified mount'), indicating this is a lightweight verification step. It does not explicitly list alternative tools or state when not to use it, but the context is strong enough for an agent to route himself.

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