Skip to main content
Glama

ctxstore — memory that follows you across models

Reinforce Fact (recall-on-success)

reinforce_fact

Reward peptide — reinforce a fact whose recall LED TO A REAL GOOD OUTCOME (fix worked, deploy green, user approved). Boosts its future retrieval ranking with a bounded, time-decaying multiplier (max 1.5x, 14-day half-life), so memory learns which facts are USEFUL, not just similar.

Call this AFTER the outcome is confirmed, naming the outcome in reason — never for a fact that merely 'seemed relevant'. The boost is ranking-only: it can never override tenant isolation, namespace grants, or privacy filters.

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": {
      "reason": "<reason>"
    },
    "name": "reinforce_fact"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoExact fact key — reinforces the current version. Provide this OR fact_id.
reasonYesREQUIRED. The concrete outcome this recall led to, e.g. 'used this fact to fix #492; deploy went green'. Rewards must trace to real outcomes.
weightNoReward strength 0-3 (default 1). Use ~0.5 for minor wins, 1 for a confirmed success, 2-3 for major verified outcomes.
fact_idNoUUID of the fact to reinforce (from search results). Provide this OR key.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (which only say readOnlyHint=false, destructiveHint=false, idempotentHint=false), the description discloses the effect size and decay ('max 1.5x, 14-day half-life'), the scope of the effect ('ranking-only'), and explicit safety boundaries ('can never override tenant isolation, namespace grants, or privacy filters'). That is exactly the mutation semantics an agent needs before invoking a non-read-only, non-idempotent write.

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?

Two paragraphs, front-loaded with the verb and the precondition, then the mechanism and guardrails. The lead-in 'Reward peptide —' is decorative framing that does not add information an agent can act on, but the rest is dense and non-redundant.

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 four-parameter mutation with no output schema, the definition covers purpose, timing, magnitude, decay, and safety limits. It does not state what a call returns or whether repeated reinforcements compound toward the 1.5x cap (relevant given idempotentHint=false), which is the remaining gap.

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

Parameters3/5

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

Schema description coverage is 100%, so every parameter including key/fact_id mutual exclusivity, weight scale, and reason requirements is already documented in the schema. The description only echoes the `reason` requirement ('naming the outcome in `reason`') and adds no format or edge-case guidance beyond it; the baseline of 3 applies.

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 ('reinforce a fact whose recall LED TO A REAL GOOD OUTCOME') and even specifies the mechanism ('bounded, time-decaying multiplier (max 1.5x, 14-day half-life)'), so the agent knows exactly what changes. It never names a sibling such as mark_salient or store_fact, so differentiation from neighboring tools is left to inference rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Timing and gating are explicit: 'Call this AFTER the outcome is confirmed' plus a hard exclusion, 'never for a fact that merely "seemed relevant"'. What is missing is any named alternative for the rejected cases (e.g., where to record a merely-relevant fact instead), so the agent must infer the fallback.

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.