Skip to main content
Glama

Best next steps

best_next_steps

Routing recommendation: the strongest next cognitive steps from a given node, by learned edge weight and trust.

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>",
      "from_node": "<from_node>"
    },
    "name": "best_next_steps"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoOptional. How many next steps to return. Default 3.
agent_idYesThe developmental agent's id, from create_agent.
from_nodeYesThe node to route onward from.

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 / from_node / description
      Added value: +"The node to route onward from."
    • addedInput schema / properties / limit / description
      Added value: +"Optional. How many next steps to return. Default 3."
  2. First observed

TDQS

B3.2/5.0
Behavior2/5

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

Annotations declare readOnlyHint=false and idempotentHint=false, which suggests the call has side effects or non-repeatable state, yet the description calls it a 'recommendation' with no mention of writes, logging, or why repeat calls may differ. 'Trust' and 'learned edge weight' are also left unexplained as scoring mechanics. With no annotations-free burden relief here, this is a real gap an agent could trip over.

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?

A single front-loaded sentence with the category label first and the ranking criterion second; nothing is wasted. It is terse enough that it reads slightly like a tagline rather than a spec, but structurally sound.

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

Completeness3/5

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

An output schema exists, so return values need not be described, but for a tool with mutation-flagged annotations and a learning-based ranking model, the definition leaves the side-effect profile and the meaning of 'trust' unaddressed. It is adequate to identify the tool but not to predict its behavior.

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 all three parameters are already documented, and the description only adds the notion that from_node is the origin of ranking and that results are ordered by learned weight and trust. It says nothing extra about limit or agent_id. Baseline 3 is appropriate.

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?

Names a specific output (routing recommendation of next cognitive steps from a given node) and the ranking basis (learned edge weight and trust). An agent can distinguish it from route_task or record_route_outcome because it is framed as a recommendation rather than an action or a write-back. It stops short of explicitly contrasting itself with those siblings.

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 'Routing recommendation' implies advisory use before acting, but the description never states when to call this versus route_task, nor any preconditions such as whether the node must already have learned edges. Usage is inferable rather than stated.

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.