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

Annotations already declare readOnlyHint and idempotentHint. The description adds value by specifying sort order (newest-and-largest first), default recency window (90 days), and that an empty list with note indicates no changes. It also clarifies the data format (before→after change). No contradictions.

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 well-crafted sentences front-load the core action, then add filtering options and result behavior. No filler words. Every sentence adds distinct value.

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?

No output schema exists, but the description gives a basic understanding of the return format (dated before→after change) and empty list handling. Could be more explicit about fields, but overall sufficient given the tool's read-only nature and annotations.

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% with detailed param descriptions. The description repeats default for withinDays and filter options but does not add new information beyond what the schema already provides for each parameter.

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 it lists recorded price moves across the index within a recency window, sorted newest-and-largest first, with optional filters. It distinguishes from siblings like 'get_price_history' or 'volatility_for_entity' by focusing on aggregated changes rather than time series or volatility metrics.

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 implies usage for recent price moves, especially with the phrase 'freshness a base model structurally cannot have,' but does not explicitly state when to use this tool over alternatives like 'whats_changed' or 'volatility_for_entity'. No when-not-to-use or exclusions are provided.

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