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

Beyond the annotations (readOnly=false, idempotent=true, destructive=false), the description discloses real behavioral traits: it blocks in the caller runtime 'without polling,' yields a 'service-signed receipt' on close, and explicitly cannot 'prove external silence or pause unrelated work.' This negative-scope disclosure is genuinely useful and not derivable from structured fields, though it omits failure/retry behavior.

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 definition is compact and front-loads the core concept, with each clause adding a distinct constraint (authorization, consent, boundary, non-guarantees) rather than padding. It is terse to the point of being elliptical in places, but no sentence is wasted.

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 7-parameter tool with a 4-value action enum, only 1 required parameter, no output schema, and 14% schema coverage, the description is missing too much: the per-action semantics and most parameter meanings are unexplained. The behavioral framing is strong but the invocation-level detail an agent needs is absent.

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 only 14% (just account_ref), and the description does not compensate: it never explains the action enum values (start/read/close/list), pause_seconds, checkpoint_id, request_key, consent, or operator_authorized. At 7 parameters with near-zero coverage, the description should carry more but adds no mapping between prose and individual parameters.

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 frames the tool as an 'optional paid-continuity boundary between tasks,' which conveys the general concept but never clearly states that it starts/reads/closes/lists a checkpoint. It hints at a lifecycle ('start,' 'close for a receipt') without naming the concrete operation, so an agent must infer purpose from the action enum. It is distinguishable from siblings like eclypse_pause by tone but not by explicit contrast.

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?

It gives precondition-style guidance — 'Start only with operator authorization, processing consent and a safe local boundary' — which implies when the tool may be invoked. However, it never names alternatives (eclypse_pause, eclypse_dwell, eclypse_continuity) or states when this tool should be preferred over them, leaving the routing decision to inference.

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