Skip to main content
Glama

Gated recall — answers only if safe to act on

safe_recall
Read-only

Answers only when every underlying fact passes the safety policy; otherwise withholds the answer and returns why, preventing irreversible actions based on disputed, stale, or low-confidence facts.

Instructions

Like recall, but for when the agent will ACT on the answer. It answers only if every current fact behind the answer passes the safety policy; otherwise it withholds the answer and returns the reasons (disputed value, low confidence, stale, or nothing current). Use this instead of recall on the path to an irreversible action.

critical_categories behaves as in recall, and matters more here: this gate can only judge the facts it was handed, so a critical fact ranked out of context would be invisible to the check as well — it would pass, on an answer it never knew was incomplete.

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": {
      "question": "<question>"
    },
    "name": "safe_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_idNo
user_idNodefault
agent_idNo
questionYes
min_confidenceNo
require_activeNo
block_on_flaggedNo
max_staleness_daysNo
critical_categoriesNo
block_on_recent_change_daysNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the substantive behavior: answers are withheld on policy failure and the reasons are returned, enumerated as disputed value, low confidence, stale, or nothing current. It also discloses a real limitation of the gate — it can only judge facts it was handed — which is exactly the kind of caveat annotations cannot express.

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?

Two short paragraphs, front-loaded with the differentiator and then the one parameter caveat that changes behavior. No filler, no restatement of the title.

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 10-parameter gated tool with an output schema and read-only annotations, the description covers purpose, when-to-use, failure output, and the key scope trap. The remaining gap is how the threshold/blocking parameters compose into the safety decision, which an agent must currently guess from parameter names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 10 parameters, so the description carries the full burden and only addresses `critical_categories` (well, including its interaction with ranking/context). The gate-tuning parameters — min_confidence, require_active, block_on_flagged, max_staleness_days, block_on_recent_change_days — are left entirely to self-describing names, with no indication of how they interact with the stated safety policy.

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 description states a specific verb and resource ('answers' a question from recalled facts) and immediately contrasts the scope with the sibling `recall`: this one gates on a safety policy and withholds instead of answering. An agent can tell exactly what it returns on success versus failure.

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 names the alternative explicitly ('Use this instead of `recall` on the path to an irreversible action'), giving both the selecting condition and the exclusion. The implied complement — use plain `recall` when the answer is informational — follows directly from that framing.

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