Skip to main content
Glama

backlog_recall

Recall past knowledge and episodes captured across sessions using free-text queries, with stubs or full memory bodies, filtered by tags, layers, and context.

Instructions

Recall memories — knowledge and episodes captured across sessions. Returns STUBS (title + one-line digest + provenance) by default; expand interesting ones with backlog_get(MEMO-id), or pass full:true for bodies. Weigh a stub's trust BEFORE hydrating: age_days (on the knowledge's own timeline), uses/idle_days (recall demand), supersedes (this is a correction), derived (consolidator inference), kind (current/historical/plan/preference/timeless). Old + never-used = treat as hypothesis, not truth. Distinct from backlog_search (live entities). Use to answer "how do we deploy?", "have I hit this before?", "what did I finish about X?". Memories point back to source entities via entity_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoReturn full memory bodies instead of stubs. Prefer stubs + backlog_get for the ones you need.
homeNoSelect the document home for this read. "all" queries global plus the explicitly supplied/bridged project root; it never scans prior projects.
tagsNoFilter by memory tags (any-match). e.g. ["artifact"] or ["task"].
limitNoMax results. Default: 10.
queryYesFree-text query (keyword or phrase).
layersNoRestrict to specific memory layers. Default: all persisted layers (episodic + semantic + procedural).
contextNoOptional scope — usually a parent_id like "FLDR-0001". Filters to memories captured with that entity as their context.
project_rootNoProject root for this call. Overrides the bridge project root and selects the project home.
token_budgetNoApproximate token budget — results are greedily packed to fit.
Behavior5/5

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

No annotations; description compensates fully. Explains stub format (title, digest, provenance), trust fields (age_days, uses/idle_days, supersedes, derived, kind), and interpretation ('Old + never-used = treat as hypothesis'). Also mentions entity_id linking back to source entities.

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?

Well-structured: purpose, output description, trust guidance, usage examples. Length is justified by richness of info; slightly verbose but no waste.

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

Completeness5/5

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

Given 9 parameters, no output schema, description fully explains return format, trust interpretation, and usage contexts. Covers all necessary aspects.

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%, so baseline is 3. Description adds context like 'prefer stubs + backlog_get' but doesn't provide new parameter semantics beyond schema.

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

Purpose5/5

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

Clearly states 'Recall memories — knowledge and episodes captured across sessions.' Distinguishes from backlog_search (live entities) and backlog_get (for expanding stubs).

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?

Explicitly provides example queries ('how do we deploy?', 'have I hit this before?') and contrasts with backlog_search. Gives guidance on stub vs full retrieval.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/gkoreli/backlog-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server