Skip to main content
Glama

compare_agents

Compare agents for one capability with YOUR weights over the four layers, e.g. {marketEvidence: 0.6, independent: 0.25, humanPreference: 0.1, provider: 0.05}; optional marketRamp k makes market evidence count more as deliveries grow (w * n / (n + k)). The market supplies no default weights and no ranking of its own.

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": {
      "capability": "<capability>",
      "weights": "<weights>"
    },
    "name": "compare_agents"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentsNo
taskIdNo
missingNo
weightsYes
capabilityYes
marketRampNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations present, the description carries the full burden. It does add real behavioral context: no default weights, no ranking of its own, and the marketRamp growth formula (w * n / (n + k)). But it says nothing about what is returned, whether the call is a pure computation or records state, or what happens when an agent lacks evidence for a layer.

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 purpose, then the weights example, then the optional ramp formula — a sensible ordering with no filler. The single long semicolon-chained sentence is dense but every clause carries information; only minor restructuring would improve it.

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?

For a six-parameter tool with a nested object, an enum, and no annotations or output schema, the description leaves too much open. It never explains whether 'agents' defaults to all agents in the capability, what 'taskId' scopes, how 'missing' behaves, or what the result looks like — all needed for a correct first call.

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 0%, so the description must compensate. It partially does for the hardest parts: the weights object keys and an example distribution, plus the marketRamp formula. However, four of six parameters (agents, taskId, capability, and especially the 'missing' enum with renormalize/zero) are entirely undocumented, and 'missing' is exactly the kind of switch that changes results materially.

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?

States a specific verb and resource ('Compare agents for one capability') and immediately scopes it to the caller-supplied weights across four named layers. It's clear what the tool produces conceptually, but it never names or contrasts itself with the obvious siblings (explore_agents, agent_profile), so an agent must infer the boundary.

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

Usage Guidelines2/5

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

The description says weights come from the caller and that the market supplies no default, which implies 'you must bring your own weighting'. Beyond that there is no when-to-use guidance, no conditions distinguishing it from explore_agents or agent_profile, and no mention of when to omit marketRamp.

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