Compare Etsy, eBay and Amazon for one product

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

Annotations already cover read-only, idempotent and non-destructive, so the bar is low, yet the description adds real behavioral context: strict input validation that rejects unknown arguments by name rather than silently adjusting, the guarantee that results come from the same fee engine as the site's free calculators, and the unit conventions for money and percents. It also discloses what the response contains (fee breakdown, assumptions, fee table version and date, source URLs).

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?

Four sentences, zero filler, with the comparison scope and the amazon prerequisite front-loaded before unit conventions and return contents. Every sentence carries distinct information that affects either selection or correct invocation.

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 nested tool with an output schema and full annotation coverage, the description supplies the essentials: required inputs, unit semantics, validation behavior, and the target_margin_pct inversion. The residual gap is the cents-vs-USD wording ambiguity around monetary inputs, which a careful agent could trip on.

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%, so the baseline is 3, but the description adds cross-cutting meaning the schema cannot: all *_pct values are percents where 8.25 means 8.25%, and the amazon object's category/fulfillment plus dimensions/weight requirement for FBA. One note of ambiguity: 'Money is in whole cents' sits alongside schema fields documented as 'USD', which an agent could misread as the input unit for price.

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 specific verb (compare) and resource (the same product across Etsy, eBay and Amazon), and enumerates the outputs: fees, profit, margin and break-even price. This clearly distinguishes it from the twelve single-marketplace siblings such as amazon_fees and ebay_profit without the agent needing to open a schema.

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?

Gives clear context for use (one product, three marketplaces, 'One call, one charge') plus the prerequisite that the amazon object is required. However it never explicitly names the single-marketplace siblings as the alternative it replaces, so the routing decision is left mildly implicit.

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