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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavioral content: 'under preregistered rules' signals a fixed, non-discretionary methodology, and 'Zero differs from missing' warns that zero values are observations rather than absent data. What remains unstated is the coverage universe (BTC only? ETH per the subscriber line?) and the temporal extent of an episode.

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 short fragments with no filler and the substantive scope statement is front-loaded. But the final fragment 'Subscriber exit_desk_full: ETH.' is telegraphic to the point of being unparseable without insider context, so terseness here costs comprehension rather than earning efficiency.

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 zero-parameter, read-only tool this is close to adequate, and the zero-vs-missing rule is exactly the kind of caveat that matters. With no output schema present, however, the description should say more about what an 'episode' record contains beyond naming onset/trough/recovery, and the ambiguous ETH/subscriber clause leaves the asset universe genuinely unclear.

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 tool takes zero parameters, so there is no parameter semantics for the description to carry and the baseline of 4 applies. The only semantic clarification offered ('Zero differs from missing') concerns output interpretation rather than inputs, which is appropriate for a parameterless call.

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 core phrase 'BTC depth-collapse onset/trough/recovery under preregistered rules' does name a specific resource and its phases, so an agent can infer it returns realized market-depth collapse episodes. However, the trailing fragment 'Subscriber exit_desk_full: ETH.' introduces an unexplained ETH reference that blurs whether the tool covers BTC, ETH, or both, and nothing distinguishes it from siblings like unwind_watch, liquidity_tiers, or exit_cost.

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?

There is no statement of when to use this tool versus the many adjacent sibling tools (unwind_watch, exit_cost, venue_concentration all concern exits/liquidity). The 'Subscriber exit_desk_full' fragment hints at an access tier but never states a condition, prerequisite, or exclusion an agent could act on.

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