Skip to main content
Glama

TeamShared

by io.github.xhad

Memory Think

memory_think

Synthesized answer with citations and gap analysis (GBrain think parity).

Runs durable recall (default scope excludes working), then composes a cited prose answer plus explicit gaps. For named-entity or competitor questions, call memory_recall with a short keyword anchor first — synthesis quality depends on retrieval. Prefer memory_think when you need prose + gaps after recall surfaced hits, or for open strategic questions. Default sources are current truth; pass include_superseded=true to include retired facts.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoMax source records to retrieve before synthesis
repoNoWorkspace slug; boosts repo-scoped memories in retrieval
queryYesQuestion to answer from team memory
githubNoGitHub owner/repo; boosts github-tagged memories
token_budgetNoApprox token budget for source packing
include_supersededNoWhen true, synthesize from current truth plus superseded/merged history. Default is current truth only.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / include_superseded
      Added value: +{
+  "default": false,
+  "description": "When true, synthesize from current truth plus superseded/merged history. Default is current truth only.",
+  "type": "boolean"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden, and it does well: it states the internal sequence (durable recall, then a cited prose answer plus gaps), the default exclusion of working-memory scope, and the current-truth-only default. It does not explicitly declare that the tool has no mutating side effects, but the described behavior strongly implies a read/synthesize operation.

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

Conciseness5/5

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

The description is information-dense with no filler: every sentence contributes either a definition, a usage rule, a warning about retrieval dependency, or a key default behavior. The most important identifier is front-loaded first.

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 the output schema exists and the input schema documents all parameters, the description covers the remaining contextual needs: when to use this tool versus memory_recall, how retrieval affects quality, what scope is used by default, and how to switch to superseded history. Nothing critical is missing for correct invocation.

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 description coverage is 100%, so the schema already fully documents every parameter. The description adds a small amount of extra semantic nuance for include_superseded and the retrieval-dependent nature of quality, but it does not materially enrich k, repo, github, or token_budget beyond their schema descriptions.

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?

The description opens with a specific verb+resource statement: 'Synthesized answer with citations and gap analysis', which clearly defines what the tool produces. It also distinguishes itself from memory_recall by positioning this as the 'prose + gaps' layer after recall has surfaced hits, so it is not confusable with sibling memory tools.

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?

The description gives explicit routing guidance: named-entity/competitor questions should call memory_recall first, while memory_think is preferred for prose-plus-gaps or open strategic questions. It also explains that synthesis quality depends on retrieval, telling the agent when a prerequisite step is needed.

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

All TeamShared toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.4/5.0
Disambiguation4/5

With 104 tools across many domains (memory, work, projects, files, agents, context, strategic, ontology), the use of clear prefixes (memory_, work_, project_, file_, agent_run_, context_) makes most tools distinct. However, there are some potential confusions between memory_session_* vs memory_state_*, and memory_recall vs memory_think vs memory_assemble_context, though descriptions clarify their specific purposes. Aliases like memory_playbook_get for memory_procedure_get are explicit and reduce ambiguity.

Naming Consistency5/5

Tool names follow a highly consistent pattern: prefix_domain_action (e.g., file_create, work_update, memory_recall, agent_run_start). All use snake_case, with verbs consistently placed after the domain prefix. Even less common tools like account_brief and attention_snapshot fit the overall naming scheme, making the set predictable and easy to navigate.

Tool Count3/5

At 104 tools, this is an exceptionally large surface area, far exceeding the 25+ threshold that feels heavy. However, the server covers an extensive domain (organizational memory, work management, project tracking, file sharing, agent orchestration, and strategic planning), which justifies a large count. Still, the sheer number may overwhelm agents, and some tools could be consolidated (e.g., many memory_session_* and memory_state_* variants).

Completeness4/5

The tool surface is remarkably complete for its stated purpose, covering CRUD operations for files, work items, projects, and memory, plus lifecycle management for agents, sessions, and strategic plans. Minor gaps exist (e.g., no direct memory_item_get by ID, no section removal in projects), but agents can work around these using existing tools like memory_recall or work_create with parent_id. Overall, the set minimizes dead ends.

Resources