Skip to main content
Glama

Apply what works to a plan

apply_performance_learnings

Write the workspace's current measured findings (engagement rate, CTR, format, slot, hook) into a plan's brief, so every asset that plan produces next is briefed from evidence. Refuses below the minimum sample instead of inventing a pattern. This changes the brief; it does not regenerate existing assets.

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": {
      "plan_id": "<plan_id>"
    },
    "name": "apply_performance_learnings"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNoMeasurement window in days
plan_idYesThe plan whose future content should learn from results

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description's job is to add scope, which it does: it mutates the brief only, leaves existing assets untouched, and fails closed below a minimum sample. It stops short of saying whether existing brief content is overwritten or merged, and it does not state permission requirements.

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?

Three tight sentences, front-loaded with the action and its payoff, then the failure mode, then the scope boundary. Every sentence carries distinct information and none restates the tool name or the schema.

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 mutation tool with annotations but no output schema, the definition covers what is written, what is left alone, and when it will refuse. The main residual gap is that with no output schema the agent has no description of what it gets back or how to confirm which findings were applied.

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 coverage is 100%, so both parameters are already documented in the schema, which sets the baseline at 3. The description implies that findings come from a measurement window but adds no clarification of what the days parameter controls or how it interacts with the minimum-sample refusal.

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 states a specific verb and resource: it writes measured findings (engagement rate, CTR, format, slot, hook) into a plan's brief, and it explicitly scopes the effect to future assets rather than existing ones. That is far more specific than the title alone. The one gap is that it does not name or distinguish itself from the sibling update_plan_brief, which plausibly also modifies a brief, so an agent must infer the split from the 'measured findings' framing.

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?

It gives a clear use context ('so every asset that plan produces next is briefed from evidence') and an explicit guard condition ('Refuses below the minimum sample instead of inventing a pattern'). It does not, however, name an alternative such as update_plan_brief or get_performance_digest for the case where the agent only wants to read findings rather than commit them to a brief.

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.

Resources