delega-mcp

recall

Search decision-memory across all tasks to surface relevant prior decisions, facts, or constraints before starting new work, avoiding re-deciding settled questions.

Instructions

Search your decision-memory across ALL tasks — recall a prior decision, fact, or constraint without knowing which task recorded it. Returns the best-matching context entries (key, value, source, and the task they live on) ranked by relevance, with human-stated facts weighted highest. Use at the START of new work to avoid re-deciding something already settled. Lexical match for now (exact-ish terms beat paraphrases). Read-only; scoped to what you can read. Hosted API only.

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": {
      "q": "<q>"
    },
    "name": "recall"
  }
}

Input Schema

Name	Required	Description
`q`	Yes	What you're about to do or looking for, e.g. 'auth token expiry policy' or 'D1 migration approach'
`key`	No	Restrict to a specific context key
`limit`	No	Max results (default 20)
`source`	No	Restrict to a provenance source
`project_id`	No	Restrict to one project
`include_superseded`	No	Include retracted/overwritten entries (default false)

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.19.0Sep 11, 2026
- removedInput schema / properties / project_id / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "number"
-  }
-]
```
- addedInput schema / properties / project_id / type
```
Added value: +[
+  "string",
+  "number"
+]
```
Addedv1.13.1Jul 25, 2026

TDQS

A4.6/5.0

Behavior4/5

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

No annotations provided, so the description carries the full burden. It discloses read-only status, scoping ('scoped to what you can read'), ranking behavior ('human-stated facts weighted highest'), and environment constraint ('Hosted API only'). Missing only rate limits/pagination, but substantially covers behavior.

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-loads the core action and scope, then usage timing, then behavior notes. Dense but every clause earns its place; the 'Lexical match for now' aside is a minor tangent but useful.

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?

Complete for a read-only search tool with no output schema: return shape described ('key, value, source, and the task they live on'), scoping, ranking, and constraints all covered. An agent has enough to call it correctly.

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 coverage is 100%, so baseline is 3, but the description adds value beyond it: ranking behavior for source values and the default-false semantics of include_superseded with retracted entries explained. The query intent example reinforces the 'q' parameter's purpose.

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?

States a specific verb and resource ('Search your decision-memory') plus a differentiating scope ('across ALL tasks'). Contrasts with sibling get_task_context implicitly by emphasizing recall without knowing the task, making it distinguishable from task-scoped context 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?

Explicit when-to-use ('at the START of new work to avoid re-deciding something already settled') and a stated match-mode limitation ('Lexical match for now... exact-ish terms beat paraphrases'). Gives the agent clear invocation conditions.

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