Skip to main content
Glama
Sign In
dreamd

dreamd

by botzrDev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

search_nodes

Search memory of events and lessons to recall prior discussions and decisions at the start of a task using a plain-text query.

Instructions

Search memory (events + lessons) at the start of the current task -- use when: the user's request, recall, did we discuss, what did we decide, previously decided. Hits mix raw events (source=episodic, recent/specific) and consolidated lessons (source=semantic, recurring patterns), ranked together by BM25 × salience. There is no layer argument. Factor citations are on GET /api/v1/recall?explain=1 only; this tool does not take explain. Pass plain words from the user's request: a colon is query syntax, and a skill_action pasted as the query fails.

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": "search_nodes"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoMaximum number of results to return (default [`DEFAULT_RECALL_K`]).
queryYesFree-text search query (BM25 × salience).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.2.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses the two result sources by source tag, the ranking function (BM25 × salience), the absence of layer and explain parameters, and a failure mode (a skill_action pasted as the query fails, a colon is query syntax). That is substantially more than the annotation-free baseline requires.

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 then triggers, with behavioral caveats following — good ordering and no filler sentences. It is dense with dashes and API-path references, which costs a little readability but each clause (no layer arg, no explain arg, query-syntax warning) prevents a distinct misuse.

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 two-parameter, annotation-free, output-schema-less search tool, the description covers ranking, result composition, and query construction, which is most of what an agent needs. It stops short of describing the shape of an individual hit or what an empty result means, so a small gap remains.

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, but the description adds real meaning to query that the schema does not: pass plain words from the user's request, colons are parsed as syntax, and structured action strings will fail. The k parameter is left entirely to the schema, which is acceptable since it is already documented.

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 memory (events + lessons)") and immediately characterizes what a result set contains: raw episodic events mixed with consolidated semantic lessons. That makes it unambiguously distinct from its only sibling append_node, which is a write path, without needing the 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?

Supplies explicit trigger phrases ("recall," "did we discuss," "what did we decide," "previously decided") that map the tool to concrete user intents. It also routes the agent away from false expectations by naming the alternative surface for citations (GET /api/v1/recall?explain=1) and stating "There is no layer argument."

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

Deploy Server

Other Tools