Canonical earn products & variants

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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds context beyond these: it confirms the graph includes confidence with bands, verification timestamps, and geo eligibility resolved from variant overrides or provider defaults. This is useful behavioral detail. However, it doesn't specify pagination behavior or what happens if the result set is very large.

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 two sentences: the first concisely enumerates the rich output structure, and the second gives a clear usage case. It is dense with information but not excessively long. Slightly more structure (e.g., bullet points for variant fields) could improve readability, but it remains effective.

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?

Given the tool has 6 optional parameters and a moderate schema coverage of 67%, the description sufficiently covers the key data fields and usage intent. The output schema exists but is not shown here; if it documents the return structure well, the description is adequate. It could be more complete by mentioning the default page size or the behavior of min_confidence filtering on variant-level data, but these are minor gaps.

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 67% (4 of 6 params have descriptions). The description goes beyond the schema by explaining the overall data model and the meaning of the returned fields (e.g., confidence bands, geo eligibility), which helps the agent understand how filters like symbol, provider, or min_confidence relate to the output. This adds value but doesn't describe each parameter's syntax in detail.

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 clearly states that the tool returns 'the canonical earn product graph' with detailed term variants. It moves beyond the generic title by specifying the data structure (provider x asset x category) and listing key fields (lockups, tiers, minimum deposits, etc.). This effectively distinguishes it from sibling tools that focus on prices, rates, or coin details.

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 closes with a direct usage cue: 'Use for "what are the actual terms behind this rate?"' This tells the agent exactly when to select this tool over alternatives like get_rates or get_price. It implicitly advises against using it for simple price lookups, which are handled by siblings.

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