Skip to main content
Glama

recall_bundle

Collect the facts recall skills depend on without a model call: list changes since a date or gather session logs, decisions, open tasks and graph entities for a project.

Instructions

Collect, without calling a model, the facts the recall skills build on. mode='digest' lists what changed after a date (7 days ago when omitted). mode='resume' gathers session logs, decisions, open tasks and graph entities whose project contains the given text, ignoring case. A section that fails does not stop the others.

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": {
      "mode": "<mode>"
    },
    "name": "recall_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeYes
sinceNo
projectNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full burden and does real work: it states the collection happens 'without calling a model', discloses the default lookup window, notes case-insensitive matching, and adds a fault-isolation trait ('A section that fails does not stop the others') that an agent could not guess. It leaves the return shape and whether the operation is strictly read-only implicit.

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?

Three sentences, front-loaded with the core verb and the no-model trait, then the modes, then failure behavior; there is essentially no filler. The mode clauses are dense but readable, with only mild compression in the 'graph entities whose project contains the given text' phrasing.

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?

For a three-parameter, annotation-free tool with no output schema, the definition covers mode semantics, defaults, matching behavior, and partial-failure handling, which is close to what an agent needs to call it correctly. The remaining gap is the exact shape of the returned sections, particularly what 'what changed' resolves to in digest mode.

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

Parameters4/5

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

Schema description coverage is 0% and mode is not even an enum in the schema, so the description must define the parameter spaces — and it does, naming the two mode values, the default for 'since', and the substring/case-insensitive semantics of 'project'. It stops short of saying what happens with an unrecognized mode or whether 'since'/'project' are ignored in the wrong mode.

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 concrete verb and resource ('Collect ... the facts the recall skills build on') and then enumerates two named modes with distinct behaviors, so an agent can tell what the tool returns in each case. It does not explicitly contrast itself with context_bundle or the other recall-related siblings, which keeps it short of a 5.

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

Usage Guidelines3/5

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

It describes the two modes and the default for the date ('7 days ago when omitted'), which implies when each mode is appropriate. However, there is no explicit when-not guidance and no named alternative for the adjacent use cases (e.g. context_bundle, search_brain, list_recent), so routing still requires inference.

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