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

Annotations declare readOnlyHint=true, but the description adds substantial context beyond that: it explains how dca_baseline_90d is computed (weekly samples over preceding 90 UTC days, excluding latest observation), notes dca_baseline_90d_partial identifies incomplete history, and warns that metrics are pre-computed and should not be re-derived with calculate. No contradiction with annotations.

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 front-loaded with the core purpose, then compactly enumerates return metrics and usage guidance. Every sentence serves a distinct function—purpose, output details, edge-case identifier, use cases, alternative, and optimization. No redundancy or filler.

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?

The tool is complex with multiple precomputed metrics, but the description covers all key aspects: return value composition, granularity caveats, partial history handling, and guidance on avoiding re-derivation. An output schema exists, so return values need not be exhaustively spelled out, yet the description still provides a rich overview.

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 the baseline is 3. The description adds a small amount of semantic value by clarifying when stats_only is useful ('when the daily series is unnecessary'), but most parameter meaning is already fully documented in the schema. No significant gap to compensate.

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 a specific verb+resource ('Get historical price data for crypto tokens') and details the exact outputs (period statistics, daily price series, high_30d, std_30d, dca_baseline_90d). It distinguishes from siblings like get_token_price and web_search by focusing on historical time windows and time-comparative analysis.

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?

Explicit use cases are given ('Use for period comparisons (month-over-month, YTD), trend analysis, and price charts'), with a direct alternative ('Prefer over web_search for time-comparative financial queries') and a conditional optimization ('Pass stats_only=true when the daily series is unnecessary'). This is textbook usage guidance.

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