Skip to main content
Glama

edit_silicon_sample

Idempotent

Save a survey's Silicon Sample draft settings (synthetic LLM personas answering the survey) or preview the prompts a run would send. Neither calls the model nor writes responses; start_silicon_sample_run starts a run. Requires a Pro plan (or a workspace with a Pro owner).

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": {
      "survey_id": "<survey_id>"
    },
    "name": "edit_silicon_sample"
  }
}

Input Schema

NameRequiredDescriptionDefault
configNoSave the survey's shared Silicon Sample draft: LLM credential, model, persona source (panel, earlier survey, or responses), persona count, and prompt templates. Read it back with read_silicon_sample include config.
previewNoRender the prompts a run would send for up to 20 personas, without calling the model or writing anything.
survey_idYesSurvey UUID

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare non-readonly, non-destructive, idempotent and closed-world. The description adds genuine value beyond them: neither mode calls the model or writes responses, and the tool is gated behind a Pro plan or a workspace with a Pro owner — an auth/licensing constraint an agent cannot infer from annotations. Return behavior is covered by the output schema.

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?

Three short sentences, front-loaded with the action and immediately followed by the important negative claim (“neither calls the model nor writes responses”) and then the plan prerequisite. No filler; the only slight compression loss is that the two modes are joined by “or” without further disambiguation.

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?

For a nested two-mode tool with an output schema and full annotation coverage, the description supplies the essentials: what is persisted, that no model call occurs, the alternative for running, and the plan gate. Minor gaps remain (whether saving creates a draft if none exists, and whether config and preview may be sent together) but nothing that would cause a mis-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 description coverage is 100% and the nested config/preview objects document every field in depth, so the schema carries the burden. The description only summarizes the config surface (credential, model, persona source, count, templates) without adding semantics not already present in the schema. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and resource pair (“Save a survey's Silicon Sample draft settings”) plus a second explicit mode (“preview the prompts a run would send”). It names the sibling it is not (start_silicon_sample_run starts a run), so an agent can separate editing/previewing from executing without opening any schema.

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?

The description routes clearly: to actually run personas, use start_silicon_sample_run; to read back a saved draft, the schema points at read_silicon_sample with include config. It also states the Pro-plan prerequisite. It does not explicitly say when to choose the preview mode over saving settings, but the distinction (“preview the prompts a run would send” vs “save ... draft settings”) is implied clearly enough.

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