Skip to main content
Glama

Submit evaluation

submit_evaluation

Evolve an agent with one task outcome: {task_id, task_type, success_score in [0,1], optional accuracy/user_satisfaction/ cost_efficiency/safety_score/notes/used_nodes/used_edges}. Success strengthens the used edges, failure weakens them; growth and pruning follow the genome's rules under its safety axioms (NG1). Returns the new developmental-ledger events.

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": {
      "agent_id": "<agent_id>",
      "evaluation": "<evaluation>"
    },
    "name": "submit_evaluation"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idYesThe developmental agent's id, from create_agent.
evaluationYes{task_id, task_type, success_score 0..1, optional accuracy, used_nodes, used_edges}.
request_idNoOptional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / agent_id / description
      Added value: +"The developmental agent's id, from create_agent."
    • addedInput schema / properties / evaluation / description
      Added value: +"{task_id, task_type, success_score 0..1, optional accuracy, used_nodes, used_edges}."
    • addedInput schema / properties / request_id / description
      Added value: +"Optional. Your id for this call. Repeat it to retry safely: the same request_id is never charged twice."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false; the description adds real substance beyond that - success strengthens used edges, failure weakens them, and growth/pruning follow the genome's safety axioms (NG1). It also states what is returned (new developmental-ledger events). It still omits whether a single bad score can permanently prune structure and how strongly one outcome moves the genome.

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?

Front-loaded with the action and only three sentences, each carrying distinct information (payload, mechanism, return). The brace-notation payload list is dense and duplicates the schema somewhat, but nothing is padding.

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?

An output schema exists, so the brief return mention suffices, and all three top-level params including request_id retry semantics are covered in schema. For a state-mutating tool with nested free-form evaluation data, the description is close to complete; only the strength/magnitude of the learning effect and any preconditions are missing.

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, but the description actually adds fields the schema summary omits - user_satisfaction, cost_efficiency, safety_score, notes - and gives the 0..1 bound on success_score in prose. It does not explain how success_score is thresholded or what used_nodes/used_edges should contain.

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 opens with a specific verb+resource: 'Evolve an agent with one task outcome', and immediately enumerates the payload so the agent knows this is the learning/feedback path. It never names a sibling (e.g. record_route_outcome) to differentiate itself, so an agent must infer the split from the name alone.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: submitting a task outcome is what triggers edge strengthening/weakening, so the agent can infer 'call after a task completes'. There is no explicit when-not guidance, no prerequisite (e.g. agent must exist / be in a developmental state), and no routing against record_route_outcome or best_next_steps.

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.