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

Annotations already declare readOnlyHint and destructiveHint, but the description adds genuinely useful behavior: page-paginated with default 25 / max 100, the need to walk pagination.totalItems and totalPages, and a warning never to answer totals from a single page. It also discloses the return-point shape and the exact-decimal-string precision rule, which no structured field encodes. The opening 'Read-only' merely restates annotations, but the rest carries real weight.

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?

Front-loads the purpose, then pagination, then a targeted hint for reference-list siblings. Dense but organized with a labeled 'PAGE-PAGINATED' block; the capitalized warnings are slightly heavy but each sentence carries instruction 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?

With no output schema, the description supplies the return shape ({date, balance}), the numeric encoding caveat, pagination mechanics, and default date behaviors. For a paginated time-series read, an agent has everything needed to call it and interpret results 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 100%, so every parameter is already documented, including the granularity enum and the limit bounds. The description reinforces granularity as bucket size and repeats the limit default/max, but adds little parameter meaning beyond what the schema states, so the baseline applies.

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?

States a specific verb and resource — 'Get historical balance snapshots for a single asset over a date range' — and frames the scope as a time series rather than a current-state lookup, which separates it from siblings like get_balances.

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?

Explicitly says when to use it ('to chart or describe how a balance trended over time'), explains how granularity changes the result, and gives a concrete pagination rule plus a pointer to pass limit: 100 for get_assets and get_markets. The exclusions are actionable rather than implied.

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