Skip to main content
Glama
slowave

slowave

Official
by slowave-ai

slowave_recall

Retrieves semantically relevant memories and procedures into working memory for focused mid-task lookups, scoped to the active session so agents can recover needed historical context.

Instructions

Semantic retrieval: bring relevant memories into working memory. Use for deliberate mid-task lookups when you need specific historical context beyond what activate surfaced. Recall is explicitly bound to the active session and matching scope. Retrieval considers semantic meaning and specific lexical matches, then selects context relevant to the current need. Ask a focused natural-language question naming the subject, goal, and relevant conditions; preserve exact project/service names, identifiers, and error text when known. Paraphrases can match; you do not need to reproduce the stored wording. Avoid keyword stuffing or assuming the answer in the query. For example, a stored claim "Atlas authentication credentials expire after 45 minutes" can be queried with "How long do Atlas login tokens remain valid?" State independent needs as separate sentences when asking several questions. Results are bounded suggestions, not proof of truth or a complete inventory. If needed history is missing, clarify the question or use a returned continuation when more context would help; an empty result does not prove absence. Inspect provenance/evidence and procedure outcomes/caveats before applying guidance; use evidence="full" when source content is needed, noting truncation. Args: page_size: optional strict integer 1–10; omitted values use the server default for a new query. Omit with continue_from. query: natural-language query; omit when continuing a frozen result. session_id: active session returned by slowave_activate. scope: required retrieval boundary; must match the session. task_context: optional context update for this sub-question. evidence: references (default) or full; budget and policy are server-owned. continue_from: opaque cursor returned by activate or recall. The cursor is bound to this session and scope and replays a frozen tail. Returns: retrieval_id: pass to slowave_feedback after using memories. memories: canonical direct/associated memories with stable pathways. procedures: canonical procedures, including their ID, goal, summary, context, steps, caveats, outcome, outcome_summary, created_at, aggregate evidence, and recent contributions; no ranking scores. evidence: bounded records with evidence_id, source_kind, recorded_at, occurred_at, and source_ref; full mode also returns content and per-record truncated. evidence_mode: the applied references or full mode. evidence_truncated: whether evidence records exceeded the response budget. retrieval_policy_version: server-selected retrieval-policy identifier. relevant_total: number of discovered relevance-qualified declarative memories in a relevant-set response. catalog_truncated: true when the bounded candidate search could have omitted qualifying memories. more_available: whether a frozen continuation page is available. continue_from: opaque continuation cursor, present only when more_available. accessible_field: bounded orientation for unreturned candidates; contains extra_candidates, kinds, and approx_extra_tokens, never content.

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": {
      "session_id": "<session_id>",
      "scope": "<scope>"
    },
    "name": "slowave_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNo
scopeYes
evidenceNoreferences
page_sizeNo
session_idYes
task_contextNo
continue_fromNo
semantic_contextNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.20.9
    • changedInput schema / properties / query / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 200000,
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedInput schema / properties / scope / maxLength
      Added value: +200
    • changedInput schema / properties / semantic_context / anyOf
      Previous value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "maxLength": 200000,
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed1 schema field changedv0.20.5
    • addedInput schema / properties / page_size
      Added value: +{
      +  "anyOf": [
      +    {
      +      "description": "Maximum memories per page (default 5); continuations inherit this bound. Procedures have a separate limit.",
      +      "maximum": 10,
      +      "minimum": 1,
      +      "type": "integer"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "title": "Page Size"
      +}
  3. First observedv0.20.3

TDQS

A4.7/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden, and it does: results are "bounded suggestions, not proof of truth or a complete inventory," an empty result does not prove absence, retrieval is bound to the active session and matching scope, evidence defaults to references with full mode subject to truncation, and budget/policy are server-owned. It even tells the agent to inspect provenance and procedure caveats before applying guidance.

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

Conciseness3/5

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

The prose portion is front-loaded and dense with non-obvious guidance, but the Returns block re-enumerates roughly a dozen fields that the existing output schema already defines, making a large fraction of the text redundant. The Args list and the prose also restate each other (e.g., scope binding appears in both).

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 an 8-parameter, no-annotation retrieval tool, the definition covers invocation mechanics, query formulation, paging, and interpretation caveats. The return-value enumeration is redundant given the output schema, but the cross-tool detail that retrieval_id must be passed to slowave_feedback is narrative information the schema cannot express.

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 description coverage is 0%, so the lengthy Args section is doing real work: it explains page_size bounds and continuation inheritance, when to omit query, that scope must match the session, what task_context is for, when to choose evidence="full", and that continue_from replays a frozen tail. However, semantic_context is present in the input schema but is entirely absent from the Args list, leaving one parameter undocumented anywhere.

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 opening sentence names a specific verb and resource ("Semantic retrieval: bring relevant memories into working memory") and immediately distinguishes the tool from its sibling: "deliberate mid-task lookups ... beyond what activate surfaced." An agent can tell this apart from slowave_activate without opening either 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?

Explicit when-to-use (deliberate mid-task lookup for specific historical context), explicit alternative (activate for ambient surfacing, continue_from when more context would help), and explicit anti-patterns (avoid keyword stuffing, don't assume the answer in the query, split independent needs into separate sentences). It also prescribes query style with a worked example containing an actual stored claim and a paraphrase query.

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