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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description necessarily adds value beyond them. It does so by specifying that exact decimals, source post, provider/series, and fixture labels are retained, which informs the agent about data granularity and composition. It also clarifies the tool is not for candles or live quotes. There is no contradiction with the annotations, and the added behavioral context is meaningful.

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 long, front-loaded with the core action and resource. The second sentence succinctly adds data granularity details and exclusions. There is no fluff, repetition, or unnecessary information. Every phrase earns its place, making it highly efficient and well-structured.

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?

This is a read-only tool with 5 parameters, no output schema, and pagination hints from limit/cursor. The description explains what data is retained (decimals, source post, provider/series) but does not describe the response structure, pagination behavior, or how to use the cursor. Given the absence of an output schema, the description should provide more context about the returned data and iteration mechanics. It covers the essence but leaves meaningful gaps for an agent unfamiliar with the tool.

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 0%, so the description must compensate by explaining parameter meanings. The description only refers to 'asset' and 'capture-time window' in general terms, which maps to asset_id and date_from/date_to but adds no detail about format, semantics, or the pagination parameters limit and cursor. The schema provides types and patterns but no descriptions, leaving the agent to infer parameter roles from names alone. This is insufficient for the coverage gap.

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 identifies the verb 'Read' and the resource 'stored USD capture observations for an asset' with a time window. It explicitly differentiates from alternatives by stating 'Not candles, live quotes, or a selected price winner,' which distinguishes it from sibling tools like get_market_history, get_live_summary, and others. This is a specific, non-tautological purpose.

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 gives explicit exclusions ('Not candles, live quotes, or a selected price winner') which implicitly guide the agent away from this tool for those use cases. However, it does not name any specific alternative tool, leaving the agent to infer which sibling handles those scenarios. This is stronger than no guidance but lacks the direct 'use X instead' clarity that would merit a 5.

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