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

Goes well beyond the annotations by disclosing real side effects: a live conversion notifies the merchant's team and emails the credited affiliate, while test keys do neither. Combined with the plan/permission requirement, an agent knows the blast radius before calling.

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?

Three short sentences, each earning its place: what it does, what side effects it triggers, and what auth/test-mode constraints apply. No filler and the core action is front-loaded.

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 mutation with no output schema, the description covers the important behavioral surface — side effects, plan/write requirement, test-mode behavior. It does not mention what the call returns (e.g. a conversion id) or error behavior on duplicate orderId, but those are marginal given the rich schema.

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 every parameter including amount units, currency defaulting, duplicate orderId rejection and parentConversionId is already documented. The description only echoes 'a sale to credit to an affiliate' and adds no syntax or format detail beyond the schema; baseline 3 applies.

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 and resource ('Manually record a conversion') and immediately disambiguates with a parenthetical defining a conversion as a sale credited to an affiliate. This clearly separates it from list_conversions and update_conversion without opening either 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?

The word 'Manually' signals the use case (recording a sale that didn't arrive via automatic tracking), and prerequisites are given explicitly: an Ultimate or Scale plan key with write access, plus the note that test keys work but store test data. It stops short of naming an alternative tool or an explicit when-not condition.

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