Skip to main content
Glama

cognitive_few_shot_induce

Few-shot learning: induce a generalized procedural StrategyIR from 1-3 problem traces.

Extracts structural invariants (decision ordering, invariant contracts, verification rules)
and registers an initial candidate strategy immediately without requiring large training sets.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
source_modelNofew_shot_learner
strategy_nameNo
solution_traceYes
task_structure_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the burden of behavioral disclosure. It does disclose concrete behaviors: extracting structural invariants and registering an initial candidate strategy immediately. Still, it does not explain side effects of 'registers' — whether existing strategies are overwritten, whether this is reversible, or whether any verification happens.

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?

The description is two sentences, front-loads the core purpose, and every clause contributes either scope, behavioral detail, or rationale. There is no filler or repetition of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While an output schema exists, the description is incomplete for an invocation: task_structure_id is required but unexplained, the expected shape of solution_trace for '1-3 problem traces' is ambiguous, and the consequences of registering a candidate strategy are not stated. This leaves real gaps for correct use.

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%, so the description must compensate. It indirectly clarifies that solution_trace contains problem traces, but it never addresses the required task_structure_id, nor the optional strategy_name and source_model. An agent would not understand how to fill the required parameters correctly from this text alone.

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 ('induce') and resource ('generalized procedural StrategyIR'), and scopes the operation by 'from 1-3 problem traces'. It is distinguishable from sibling tools like compose_strategies or propose_strategy, though the domain jargon 'StrategyIR' is not unpacked.

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?

The phrase 'Few-shot learning' and 'from 1-3 problem traces' implies the appropriate context: use when only a few traces are available. However, there is no explicit guidance about when not to use it or how it compares to alternatives like learn_from_mistake, propose_strategy, or verify_strategy.

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