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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so safety is covered. The description adds genuinely non-obvious behavior: the call is side-effect-free with respect to connection state (it does not open a connection) and it returns a replay cursor rather than events themselves. It does not explain what 'protected' entails (credential/token requirement), whether the descriptor expires, or what the cursor replay window is.

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?

A single sentence that front-loads the return value and ends with the most decision-relevant qualifier ('without opening a connection'). No filler, though the clause about liquidation cascades and wall changes makes it slightly dense in one pass.

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 carries the burden of explaining returns, and it does name the two returned artifacts (connection descriptor and replay cursor). However, it omits how the descriptor is meant to be consumed, whether it expires or is single-use, and any auth requirement, which are material for a tool whose purpose is to hand off credentials/endpoint information.

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 100%, so both parameters are already documented, giving a baseline of 3. The description's mention of 'replay cursor' loosely connects to the `after` parameter but adds no syntax or semantics beyond the schema's 'opaque, exclusive event cursor'. It is worth noting the schema references a 'tier' that has no corresponding parameter, which the description neither clarifies nor contradicts.

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 uses a specific verb-and-resource pairing: it returns a protected event stream connection descriptor plus a replay cursor, scoped to liquidation cascades and wall changes. It also clarifies the key distinction that no connection is opened, which prevents confusion with the 'subscribe' name. It does not name or contrast with any sibling (e.g. get_liquidation_census, get_engine_read), so it stops short of full differentiation.

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?

Usage is only implied: an agent can infer this is a precursor step to obtaining a stream, and the 'without opening a connection' clause hints at a two-phase flow. There is no explicit when-to-use guidance, no statement of when to prefer this over a polling sibling, and no prerequisites such as authentication needs for the 'protected' descriptor.

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