Realized depth collapses

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

Annotations already declare readOnlyHint, openWorldHint=false, and idempotentHint, covering safety and world assumptions. The description adds valuable methodological transparency: detection rules were 'declared before any episode accrued' and episodes 'crossed the pre-registered threshold,' which signals that results are pre-committed rather than ad hoc. No conflict with annotations exists.

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 compact and front-loads the core subject and output fields in the first sentence. The usage cue is clear and efficient. The final sentence about 'subscriber exit_desk_full' is somewhat cryptic and references a tool not present in the sibling list, slightly reducing clarity, but it does not make the description bloated.

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 and no parameters, the description carries the burden of explaining what the agent will receive, and it does list the key fields: onset, trough, drawdown fraction, and recovery time. It also gives the scope (BTC ±1% aggregate depth) and the intended use case. It stops short of explaining units, date ranges, or how the threshold is defined, but it is adequate for a zero-parameter historical data 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?

The input schema is empty with zero parameters, so there are no parameter semantics to clarify. Per the baseline for zero-parameter tools, the description doesn't need to compensate for missing parameter docs. The description instead focuses on the output fields, which is appropriate here.

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 opens with a specific verb and resource: 'Realized depth-collapse episodes in BTC ±1% aggregate depth,' and enumerates the concrete outputs (onset, trough, drawdown fraction, recovery time). It clearly separates this tool from current-state liquidity views by framing it as historical 'actually broken lately' rather than 'how it looks right now.' This is specific enough to distinguish it from siblings.

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 an explicit trigger condition: 'Use when asked whether crypto liquidity has actually broken lately, as opposed to how it looks right now.' This tells an agent when to select it, though it does not name a specific alternative tool to use instead, relying on the contrast with current-snapshot views. The reference to exit_desk_full for the ETH desk adds scope context but is not a full when-not-to-use statement.

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