Skip to main content
Glama

resume_session

Restore context from previous sessions by retrieving the status board, recent checkpoints, staged work, updated memories, and critical rules, so you can continue work with shared history intact.

Instructions

Get a compact 'where we left off' digest: the status board (live entity state from tracker memories), the last checkpoints (most recent actions taken), staged work in flight, recently updated memories, critical rules that always apply, and a memory index of topics with counts. This is the authoritative record of what happened in previous sessions. Use your judgment about when the current request depends on that record: any ask that presupposes shared history — continuing work, referencing 'pending' or 'recent' things, resuming after a break — can't be answered correctly from the conversation or open files alone, however plausible they look. An open file shows what the user is looking at; this shows what was actually done last. Cheap to call, so prefer checking over assuming; skip it only when the request is clearly self-contained.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "resume_session"
  }
}

Input Schema

NameRequiredDescriptionDefault
recentNoHow many recently updated memories to include (default 10)
checkpointsNoHow many recent checkpoints to include (default 5)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.14.3

TDQS

A3.9/5.0
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 well: it discloses the returned sections as a schema-less return summary, declares the digest 'authoritative' for prior sessions, and states the cost profile ('cheap to call'), which justifies the prefer-checking default. It stops short of stating whether the call is purely read-only, whether anything is mutated or acknowledged, or any size/rounding behavior of the digest.

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

Conciseness4/5

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

Front-loaded: the first sentence states exactly what the digest contains, and usage guidance follows. It is longer than most definitions but almost every clause does work (the failure-mode and cost arguments both drive behavior). The closing clauses ('however plausible they look', 'prefer checking over assuming') restate the same point twice and could be tightened.

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

Completeness4/5

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

No output schema and no annotations, so the description must compensate — and it does by enumerating the digest's contents and explaining the decision rule for calling it. For a two-optional-parameter read tool this is close to complete; only the absence of any contrast with the sibling read tools and any note on digest size leaves a gap.

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

Parameters3/5

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

Schema coverage is 100% and both parameters ('recent', 'checkpoints') carry descriptive text with defaults, so the schema is self-sufficient. The description indirectly motivates them by listing 'last checkpoints' and 'recently updated memories' as digest sections, but adds no meaning about units, sensible ranges, or what happens at 0 — baseline 3 is right.

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 description opens with a specific verb+resource ('Get a compact "where we left off" digest') and then enumerates the exact sections returned (status board, checkpoints, staged work, recent memories, rules, memory index). It is clearly a session-context aggregator, but it never names or contrasts the overlapping siblings (get_checkpoint_log, get_memory, list_memories), so an agent must infer why this differs from those.

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

Usage Guidelines4/5

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

Strong when-to-use reasoning: asks that 'presuppose shared history' — continuing work, referencing 'pending' or 'recent' items, resuming after a break — are named explicitly, along with the failure mode of relying on the conversation or open files. It also gives an explicit exclusion ('skip it only when the request is clearly self-contained') and a default bias ('prefer checking over assuming'). What it lacks is routing to the alternatives, so an agent cannot tell when get_memory or get_checkpoint_log alone would suffice.

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