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

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds significant behavioral detail beyond that: it returns succeeded, in-flight, failed, and unknown outcomes; it warns that only unknown outcomes can hurt; and it states that anything under 'done' has already happened and should be reused rather than redone. This goes well beyond what annotations alone provide.

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 tight and well-organized: purpose and urgent usage guidance come first, followed by return categories and practical consequence, then a useful cost comparison. Every sentence earns its place with distinct information.

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?

Even without an output schema, the description tells the caller exactly what to expect: results for succeeded work, in-flight, failed, and unknown categories, plus the actionable meaning of 'done.' Combined with a single well-documented parameter and read-only annotations, the agent has enough to invoke this correctly in the stated recovery scenarios.

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 fully self-sufficient: run_id is required and described as 'The run id you passed to ratchet_begin_effect for this task,' which is clear. The description only refers to 'a run id' generically and adds no format, validation, or lifecycle details beyond the schema.

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 states a specific action ('Recall the work already gated under a run id') and connects it directly to avoiding repeated work. It also differentiates this tool from sibling list/report tools by framing it as the FIRST call when resuming and by comparing its context cost to 'listing the same effects'.

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 explicit, concrete triggers: call FIRST after a restart, handoff, or context compaction, before doing anything that might repeat work. It does not explicitly name alternative sibling tools or provide when-not conditions, though the cost comparison implies a contrast with list-style tools.

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