Skip to main content
Glama

resume

Restore a prior work thread in a new session by loading its focus, constraints, decisions, open issues, next actions, and evidence for durable context.

Instructions

Pick a thread up in a new session. When the host has no session-start hook (e.g. Codex), call it (or list_threads) first, before any other work. Durable state as it stands now, seven fields: focus · anchor (live git of this worktree: branch, HEAD, dirty) · constraints · decisions (with reason and authority) · open (unresolved) · next (actions) · evidence_refs — plus repo_state (repo-scope constraints/decisions shared by every thread of the repository, titles and numbers only — inspect(ref) for the full text; if one conflicts with the thread's own, both are shown, nothing is resolved for you). mode='fresh' omits decisions and ruled-outs. Never includes how it got here: pull that with trail(case_id) or find(query) when you need it.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "case_id": "<case_id>"
    },
    "name": "resume"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNocontinuity
factsNo
case_idYes
worktreeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses the exact state shape, that repo_state is repo-scoped and shown as titles/numbers only requiring inspect(ref) for full text, and that conflicting constraints are surfaced rather than reconciled. It also discloses that mode='fresh' drops decisions and ruled-outs. Missing are the safety profile (whether resume has side effects such as marking the thread active) and failure behavior for an invalid case_id.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical instruction is correctly front-loaded in the first two sentences. However, the remainder is a single dense run-on built from parentheticals and middot-separated fragments, which is information-rich but hard to scan and could be broken into a short field list plus a separate mode/conflict note.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter, no-annotation, no-output-schema tool, the description compensates well on the return side by spelling out the seven fields plus repo_state, which is the biggest gap otherwise. It remains incomplete on the input side (three of four parameters undefined) and says nothing about side effects or error conditions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it only partly does. It explains mode='fresh' (implying 'continuity' is the default that includes decisions) but never defines case_id — notably whether it identifies a thread or a case — nor worktree, and the facts parameter is entirely unmentioned.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening 'Pick a thread up in a new session' states a specific verb and resource, and the body enumerates exactly what the returned state contains (focus, anchor, constraints, decisions, open, next, evidence_refs, repo_state). It also separates itself from history-oriented siblings by stating it 'never includes how it got here' and pointing to trail(case_id)/find(query). The only drag is idiosyncratic vocabulary (thread vs case vs repo) that forces the reader to infer relationships.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit conditional trigger: when the host has no session-start hook (e.g. Codex), call this or list_threads first, before any other work. It also names alternatives for the adjacent need — trail(case_id) or find(query) when provenance is required — so the agent knows both when to use this tool and when to route elsewhere.

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