ratchet_group_statusShows every step in a multi-step unit of work: what succeeded, what can still be undone, what has already been undone, what is irreversible, and what has an unknown outcome. Use it to answer "where did this workflow actually get to?" after a crash, without changing anything.
| Name | Required | Description | Default |
|---|---|---|---|
| group_key | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
While annotations already declare readOnlyHint=true and destructiveHint=false, the description adds the key behavioral context that no changes are made and enumerates the possible outcome states (succeeded, reversible, undone, irreversible, unknown). That meaningfully enriches what an agent knows about the tool's behavior. No contradictions with annotations.
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?
Two focused sentences, with the primary behavior and outcome categories front-loaded and the motivational use case in the second sentence. No filler or repetition of annotation flags.
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?
The description covers the tool's read-only nature and the categories of output, and the single required parameter is simple, so a basic call is understandable. However, it omits how to find or format group_key, and with no output schema it does not describe the shape or ordering of the returned status details. This is adequate but not fully complete.
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 schema has one required string, group_key, with no description, and the description never explains what group_key is or how to obtain/format it. With schema description coverage at 0%, the description needed to compensate but instead only refers to a 'multi-step unit of work' without connecting it to the parameter. The agent can infer the key identifies the group, but the definition provides no concrete semantics.
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 precise verb ('Shows every step') and names the resource ('multi-step unit of work') plus the specific status categories it reports. It is clear enough to distinguish from a generic status tool, but it does not explicitly contrast it with sibling tools like ratchet_check_effect or ratchet_circuit_status, 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?
It provides a concrete trigger: 'after a crash,' and tells the agent the question it answers ('where did this workflow actually get to?'), which is strong usage guidance. It also states 'without changing anything,' implying it is for read-only inspection rather than mutation. It does not explicitly list when to prefer a sibling tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools map to clearly distinct lifecycle phases (begin/report/resolve/heartbeat) and are strongly described, but recall, group_status, and list_effects all deal with looking up past effect or workflow state and could be confused when resuming work. The use-case guidance in the descriptions mostly disambiguates them, so this is a minor rather than systemic issue.
All tools share the ratchet_ prefix and snake_case, which gives a strong predictable family feel. However, some names follow verb_noun (begin_effect, resolve_effect) while others are noun phrases (effect_receipts, group_status, prevented_loss), so the pattern is consistent in style but not in grammatical form.
Fifteen tools is at the upper end of the ideal range, but the domain is broad enough to justify every entry: effect lifecycle, lease maintenance, state inspection, circuit breakers, policies, receipts, reconciliation, rollback, and usage. Each tool fills a distinct role with no obvious redundancy.
The surface covers the full idempotency and safety lifecycle: authorize, execute, report, heartbeat, recover from indeterminate outcomes, verify with receipts, reconcile vendor truth, roll back multi-step work, and monitor budgets and policies. There are no dead ends or missing operations that would strand an agent in this domain.