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

Annotations only declare readOnlyHint=true; the description adds a useful cost model ('cost scales with how many readings come back'), a notable behavioral trait for a paid endpoint. It also clarifies the two data-freshness modes (last closed bar vs forming bar). No contradiction with the readOnly annotation.

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 sentences with no filler: the main purpose is front-loaded, kind semantics are grouped in the second sentence, and the cost caveat is last. Every sentence adds 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 three required parameters and no output schema, the description covers the main invocation concerns: what to pass, what the modes mean, and that cost varies. It lacks an explicit return-shape note, but the term 'phases' and the sibling tools give enough context for selecting and calling 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 low (33%), so the description carries the burden for currencies and tfs. It maps 'coins' to currencies and 'timeframes' to tfs, and explains the kind enum values. It does not specify currency string formats or limits, but the schema already shows they are string arrays.

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 states a specific verb and resource: 'Get phases for several coins and timeframes in one paid call.' It clearly distinguishes itself from likely sibling get_phase by emphasizing the batch/plural nature ('several coins and timeframes') and the paid-call model.

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 context for when to use this tool: when multiple coins/timeframes are needed in one paid call. It also explains the kind modes, which guides correct invocation. It does not explicitly name get_phase as the single-item alternative, but the contrast is strongly implied and the cost-scaling note helps with batching decisions.

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