Skip to main content
Glama

cachly — Explain it once. Every AI knows it.

smart_recall

Returns the fixes, decisions and pitfalls this team already learned for the task at hand. Call it FIRST at the start of every coding task — before reading files or editing — with one line about the task, e.g. smart_recall("fix login redirect loop"). Finds lessons by meaning, not exact words. instance_id may be omitted; the configured instance is used — never guess one. Falls back to remember_context keys if no semantic match is found.

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": "smart_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMax results, 1-20 (default 8).
queryYesNatural language query to find relevant cached context
authorNoWho is recalling (optional). Counts cross-author reuse.
thresholdNoSimilarity threshold 0-1 (default: 0.78)
instance_idNoUUID of the cache instance.
context_filesNoFiles you are working on, e.g. ["src/auth/service.ts"]. Lessons learned around these files rank higher.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden, and it does disclose meaningful behavior: semantic matching rather than exact-word matching, a fallback to remember_context keys, and the rule that instance_id may be omitted in favor of the configured instance. However, it says nothing about what a returned 'lesson' looks like, whether results are ranked or scored, or how the limit/threshold defaults affect outcomes.

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?

Roughly four sentences, all front-loaded: purpose and urgency first, then matching semantics, then parameter guardrails, then fallback. No filler or repetition, and the ordering matches what an agent needs to decide before calling.

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 6-parameter read tool with no annotations and no output schema, the definition covers purpose, timing, semantic behavior, instance handling and fallback well. The remaining gap is the shape of results — with no output schema, an agent has no idea whether it gets a lesson list, scores, or file references — plus how threshold interacts with limit.

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, and the description adds real value on top: it explains that query should be one line about the task with a concrete example, that instance_id should never be guessed, and that context_files boosts ranking for lessons near those files. It does not explain threshold or limit behavior beyond the schema text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource — it returns fixes, decisions and pitfalls previously learned by the team for the current task — plus a clarifying note that matching is semantic, not keyword-based. It falls short of a 5 because it does not distinguish itself from the many sibling recall tools (recall_context, team_recall, recall_best_solution, semantic_search), so an agent must infer which retrieval tool applies.

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?

It states explicitly when to call it ('FIRST at the start of every coding task — before reading files or editing') and gives a concrete invocation example. It also defines the fallback path (remember_context keys if no semantic match) and a hard constraint (never guess an instance_id), leaving little to inference.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.