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

Goes well beyond the annotations by disclosing the transaction shape ('records the decision, requeues the same task lineage and resolves the card in one transaction') and a precise list of side effects it does NOT cause (no budget, no waiver, no recovery rung, cannot correct a frozen evidence selector). It also states the failure mode — a fixed conflict with no changes — which an agent needs to interpret a refusal.

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 recovery action and the card precondition are front-loaded, followed by the effect/no-effect breakdown and the refusal rule. Dense with jargon but each sentence adds a distinct constraint; the registration-endpoints trailing clause is the one bit that doesn't help an agent choose or call the tool.

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?

A mutation tool with an output schema, so return values needn't be explained, and annotations already cover idempotency and destructiveness; the description supplies the preconditions, atomicity, and refusal behavior. Only the exact format of decision_md and what the fixed conflict looks like are left unstated.

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 0%, so the description carries the full burden, and it does add real meaning: escalation_id must be an *open* platform_policy_conflict card tied to the postprocessor writer, and decision_md is a recovery note recorded on the new plan section. It doesn't specify string format or length, but the value constraints are materially clarified.

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?

States a specific verb+resource ('Recover a task') and narrows it to a precise case: an open platform_policy_conflict card attributed to Keelen's postprocessor writer. That is enough to separate it from generic siblings like resolve_escalation or retry_blocked_task, though the domain jargon ('postprocessor writer', 'evidence selector') assumes insider knowledge.

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?

Explicitly enumerates the when-not cases ('any other reason or origin — a ui-review-origin conflict, an internal receipt, an exhausted hold, or a budget or catalog signal — is refused'), which is strong negative guidance. It stops short of naming the sibling tool an agent should use instead for those refused cases.

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