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

Annotations already cover the safety profile (readOnly, non-destructive), and the description goes well beyond them: row ordering (newest first), bucket timestamp semantics (first_time + i x step_s), null-and-unavailable meaning, unit suffixes (_pct vs _ratio), and the constraint that timeframe applies only to global_market while indices are daily. It does not discuss pagination or response shape, but with annotations present that is a minor omission rather than a gap.

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 definition is dense but front-loads the most important semantics (scope, window-vs-history, row ordering) and gives a concrete example. However, the telegraphic phrasing ('for a total, an extreme or a change read summary, for the period covered read ranges') is compressed to the point of needing a re-read, and middle sentences pack several unrelated concepts without structure.

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?

For a 12-parameter, field-selecting read tool with no output schema and only one required parameter, the description covers the essentials an agent needs: valid fields and their meaning, history vs current, bucket dating, null handling, units, and the timeframe restriction. Remaining gaps (exact response envelope, interactions among detail/columns/limit) are mostly handled by the schema.

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 the baseline is 3; the description still adds real meaning by tying timeframe to a single field, clarifying the bucket definition behind limit and last, and decoding the _pct/_ratio suffixes that the schema does not explain. It says nothing extra about context, dry_run, or max_quota_cost beyond their schema text, so it is not fully compensatory.

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?

Opens with 'The whole crypto market, no target', which fixes the resource and implicitly contrasts with pair-targeted siblings, and the FIELDS block enumerates exactly what data can be returned (global_market, fear_greed, indices). The absence of an explicit verb is offset by the field list and the title, though an agent must read the whole field block to see the full scope.

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?

States the core usage rule explicitly: no window means current value, while since_ms/until_ms/last select history, and it routes agents to summary for totals/extremes/changes and to ranges for period coverage. It also disambiguates the two similar indices (fear_greed vs fear_greed_cmc) and points to describe_fields for units, but gives no guidance on when to prefer this tool over siblings like get_market_indicators.

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