eBay profit and margin

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds substantial context beyond them: strict input validation that names the offending field rather than silently adjusting, the exact margin formula (profit / seller revenue, tax excluded), the fee engine's provenance, and the fact that the response carries an itemized breakdown, assumptions, fee-table version/date and source URLs. That is unusually rich behavioral disclosure.

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?

Front-loaded with purpose and sized appropriately for a 12-parameter financial calculator; nearly every sentence carries information (validation behavior, output contents, fee-engine provenance). It is delivered as a single dense block, so the input-convention and output-contents material is harder to scan than it could be, but there is little true waste.

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 12-param tool with full schema descriptions and an output schema, the description is nearly complete: it covers purpose, validation posture, unit/percent conventions and what the response contains. The remaining gap is sibling routing — nothing tells the agent when to pick this over ebay_target_price or ebay_fees.

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; the description still adds value by fixing the percent convention ("8.25 means 8.25%") and defining margin. One caveat: "Money is in whole cents" sits awkwardly against the schema, which describes money arguments as USD with multipleOf 0.01 — an agent could read a $10 price as 1000, so the unit statement introduces ambiguity rather than resolving it.

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+resource+scope: "Calculate profit, margin and break-even price for an eBay.com (US) order." An agent immediately knows it is the eBay profit calculator and can distinguish it from amazon_profit/etsy_profit by the stated marketplace. However, it never differentiates itself from the closest siblings (ebay_fees, ebay_target_price), which overlap with its fee-breakdown and break-even outputs.

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 only implied: the description enumerates the cost inputs an order can have, from which an agent infers "use this when pricing an eBay order." It gives one concrete cross-reference ("See list_ebay_categories" for the category id), which is genuinely helpful routing. But there is no explicit when-to-use vs. ebay_target_price (also mentions break-even) or ebay_fees, and no stated prerequisites or exclusions.

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