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

Annotations already establish the safe read profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower, and the description adds genuinely useful behavior: missed windows appear under `gaps` and are missing data rather than quiet periods. This prevents a real misinterpretation of results. No rate limits, auth, or pagination behavior is mentioned.

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?

Four short sentences, front-loaded with the core question ('How much was liquidated') and then the two modes, with the gaps caveat last. No sentence is redundant and each carries distinct information.

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 must carry return-value meaning, and it does reasonably: it describes the ranking contents (long vs short liquidated USD), the series shape (per time bucket), and one output field (`gaps`). It leaves the hours parameter and the exact response fields otherwise unspecified, so it is complete enough but not exhaustive.

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 75% (coin, limit, interval documented; hours not), so the schema does much of the work, but the description adds meaning beyond it: coin switches between ranking and time series, and buckets are the interval of the series. It does not clarify the hours window or the limit/ranking interaction in text.

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+resource (liquidation totals) and precisely delineates the two output shapes: a market ranking when no coin is given, and a per-bucket time series when a coin is given. It does not explicitly differentiate itself from siblings like recent_liquidations or liquidation_map, so it stops short of a 5.

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 'Without a coin... With a coin...' construction tells the agent exactly which mode a given call selects, which is effective when-to-use guidance driven by the coin parameter. However, it never names alternative siblings (recent_liquidations, cascades, liquidation_map) or states when this aggregation is preferable to them.

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