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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context beyond those annotations: immutable log, time-ascending ordering via cursor, and the 31-day cap on unfiltered queries. It doesn't contradict annotations, and it enriches the agent's understanding of pagination and data scope.

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 sentences with no filler. The first sentence states the core purpose and data content, the second covers pagination, and the third addresses limitations and use cases. Every sentence earns its place, and critical information 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?

Given the complexity (7 params, output schema present), the description holistically covers what the tool returns, how pagination works, constraints on time windows, and real-world use cases. The output schema handles return-value details, so the description doesn't need to. The combination of annotations, schema, and description fully equips an agent to select and invoke 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 coverage is high (86%), so parameters are mostly self-documenting. The description adds semantic context that isn't in the schema, such as using provider or symbol to bypass the 31-day window and cursor-based time-ascending pagination. This bridges the gap between raw parameters and real-world usage patterns.

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 opens with 'The immutable rate-change log,' clearly identifying the resource and operation scope. It distinguishes itself from siblings like get_rates (current prices) and get_rate_history (historical snapshots) by emphasizing 'what changed since X?' and audit trails, with full provenance 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?

It gives explicit use cases ('Use for "what changed since X?" and audit trails') and notes a key limitation (unfiltered windows capped at 31 days) with guidance to filter by provider or symbol for deep history. However, it doesn't explicitly name alternative sibling tools or state when not to use this tool, so it stops short of a 5.

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