Swarm

List Evaluations

swarm_list_evaluations

Read-onlyIdempotent

Browse recorded assessments by Run, Artifact, evaluator or outcome. Inspect evidence with swarm_get_evaluation. This does not submit assessments or trigger follow-up work.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "swarm_list_evaluations"
  }
}

Input Schema

Name	Required	Description
`limit`	No	Page size; follow next_cursor for more.
`order`	No	asc or desc; retain the same order across pages.
`cursor`	No	Previous next_cursor; keep filters and order.
`run_id`	No	Run ID from swarm_list_runs.
`outcome`	No	Outcome using this tool's allowed values.
`space_id`	No	Space ID from swarm_list_spaces; omit if sole.
`artifact_id`	No	Artifact ID from swarm_list_artifacts.
`evaluator_agent_id`	No	Recorded evaluator agent ID filter.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 29, 2026

changedInput schema / properties / artifact_id / description

Previous value: -"ID from swarm_list_artifacts or a result."New value: +"Artifact ID from swarm_list_artifacts."

changedInput schema / properties / cursor / description

Previous value: -"Previous next_cursor; same filters and order."New value: +"Previous next_cursor; keep filters and order."

addedInput schema / properties / evaluator_agent_id / description
```
Added value: +"Recorded evaluator agent ID filter."
```

changedInput schema / properties / limit / description

Previous value: -"Page size."New value: +"Page size; follow next_cursor for more."

changedInput schema / properties / order / description

Previous value: -"Paging order."New value: +"asc or desc; retain the same order across pages."

addedInput schema / properties / outcome / description

Added value: +"Outcome using this tool's allowed values."

changedInput schema / properties / run_id / description

Previous value: -"ID from launch or swarm_list_runs."New value: +"Run ID from swarm_list_runs."

changedInput schema / properties / space_id / description

Previous value: -"Omit for a single approved Space."New value: +"Space ID from swarm_list_spaces; omit if sole."

Changed6 schema fields changedOct 29, 2026
- addedInput schema / properties / artifact_id / description
```
Added value: +"ID from swarm_list_artifacts or a result."
```
- addedInput schema / properties / cursor / description
```
Added value: +"Previous next_cursor; same filters and order."
```
- addedInput schema / properties / limit / description
```
Added value: +"Page size."
```
- addedInput schema / properties / order / description
```
Added value: +"Paging order."
```
- addedInput schema / properties / run_id / description
```
Added value: +"ID from launch or swarm_list_runs."
```
- addedInput schema / properties / space_id / description
```
Added value: +"Omit for a single approved Space."
```
First observedOct 28, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, so safety is covered. The description adds a useful negative scope statement ('does not submit assessments or trigger follow-up work'), clarifying side-effect absence beyond what annotations encode.

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 short sentences, front-loaded with the core action, then the inspecting alternative, then the negative scope. No filler.

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

Completeness5/5

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

With an output schema covering returns and full schema coverage on parameters, plus annotations covering safety, the description supplies the remaining needed context (filter axes and non-mutating scope). Nothing an agent needs to call it correctly is missing.

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 all eight parameters are self-documented with source hints. The description groups the filter axes (Run, Artifact, evaluator, outcome) which aids understanding but adds nothing about syntax, defaults, or pagination behavior beyond the schema.

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 ('Browse') and resource ('recorded assessments') and enumerates the filter dimensions (Run, Artifact, evaluator, outcome). It distinguishes itself implicitly from swarm_get_evaluation by pointing to it for evidence inspection, though it never explicitly contrasts with the sibling list tools.

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?

Gives clear routing: use swarm_get_evaluation to inspect evidence, and explicitly states the tool does not submit assessments or trigger follow-up work. No positive condition for when to pick this over other list tools is spelled out, so no exclusions beyond the mutation disclaimer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Swarm tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.