Gnosys

gnosys_recall

Read-onlyIdempotent

Retrieve relevant memories for a task as a context block, using keywords or '*' to pick items by reinforcement, confidence, and recency. Return up to 15 memories across projects.

Instructions

Recall relevant memories as a context block for a task, e.g. query="JWT middleware". query="*" selects by reinforcement, confidence, and recency; limit uses config by default and is capped at 15; aggressive defaults to config (true). Use gnosys_hybrid_search instead to inspect ranked results or gnosys_read for one complete body. Registered projectRoot includes project, user, and global memories; omit it for all projects, or run gnosys_init for an unregistered root. Installed hooks may already inject this context per prompt.

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": {
      "query": "<query>"
    },
    "name": "gnosys_recall"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Max memories to return (default from config, max 15)
`query`	Yes	What the agent is currently working on. Use keywords. Example: 'auth JWT middleware' or 'database migration schema'
`traceId`	No	Optional trace ID from the outer orchestrator for audit correlation
`aggressive`	No	Override aggressive mode for this call. Default: from gnosys.json (true)
`projectRoot`	No	Registered projectRoot searches that project plus user and global memories. An unregistered projectRoot returns an error asking for gnosys_init. Omit projectRoot to search all projects.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv7.0.0Oct 21, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond that: query="*" selects by reinforcement/confidence/recency, limit is capped at 15 and defaults from config, aggressive defaults to true, and registered projectRoots span project+user+global. It does not say what the unregistered-root failure looks like or how memory bodies are trimmed in the block, keeping it short of a 5.

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 with purpose and example, then alternatives, then parameter behavior, then scope caveats — a sensible ordering. It is dense and slightly run-on in the final two sentences, but no sentence is filler.

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?

For a 5-parameter read tool with full schema coverage and no output schema, the description supplies everything the agent needs: output form, wildcard behavior, caps, defaults, project scope, and the hook-duplication caveat.

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 the baseline is 3; the description still adds value by documenting the special wildcard value query="*" and its ranking semantics, which the schema does not mention. The limit and aggressive defaults largely restate schema text, so it is additive but not fully independent.

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?

Starts with a specific verb+resource ('Recall relevant memories') and names the exact output shape (a <gnosys-recall> context block for a task) with a concrete example query. It also explicitly distinguishes itself from gnosys_hybrid_search and gnosys_read later, so an agent can route without opening any schema.

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?

Names alternatives and the conditions that select them: 'Use gnosys_hybrid_search instead to inspect ranked results or gnosys_read for one complete body.' It also gives explicit projectRoot rules (omit for all projects, run gnosys_init for unregistered roots) and warns that hooks may already inject this context, which is a real when-not-to-call signal.

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

Deploy Server