Skip to main content
Glama

Save request

save_request
Destructive

Create or update a request in the workspace so the developer finds it in the Gostman app and can re-run it later; only supplied fields change, and secrets must be {{variable}} references.

Instructions

Create a request in the workspace, or update one by id, so the developer finds it in the Gostman app and it can be re-run later. Only the fields you give are changed. Secrets are refused: a value that matches a variable or a credential must be written as {{name}}. Returns the request's id, name, folder and new revision. An update is refused when the request changed since you read it with get_request; read it again and merge.

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": "save_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe id of the request to update. Leave out to create a new request.
urlNoRequired for a new request. Use {{variables}} for hosts and credentials, for example {{baseUrl}}/users.
bodyNoThe request body as text.
nameNoRequired for a new request.
tagsNoReplaces the request's tags, such as smoke. run_folder runs a tagged subset.
folderNoThe folder path to keep the request in, such as auth/tokens. Missing folders are created. An empty string moves it to the top level.
methodNoGET, POST and so on. Defaults to GET.
headersNoReplaces the request's headers. Credentials must be variable references.
revisionNoThe revision you last read (from get_request, list_environments or a save). The save is refused if the item has changed since. Leave out to use the one this session last saw.
body_typeNoHow the body is sent.
assertionsNoReplaces the request's checks. They run every time the request is sent, here and in the app.
extractorsNoReplaces the request's extraction rules. After each response, every rule stores a value in a session variable, so a login can hand its token to later requests as {{token}} without the token appearing in a result.
descriptionNoWhat the request does, in a sentence. Shown in the app and used as the tool description with --expose-tag.

Output Schema

NameRequiredDescriptionDefault
idNo
nameNo
noteNo
folderNo
createdNo
revisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.16.1
    • addedInput schema / properties / revision
      Added value: +{
      +  "description": "The revision you last read (from get_request, list_environments or a save). The save is refused if the item has changed since. Leave out to use the one this session last saw.",
      +  "type": "string"
      +}
    • addedOutput schema / properties / note
      Added value: +{
      +  "type": "string"
      +}
    • addedOutput schema / properties / revision
      Added value: +{
      +  "type": "string"
      +}
  2. First observedv1.7.19

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=false, but the description adds the real operational hazards: secrets are refused unless written as {{name}}, partial-field updates apply, a revision conflict aborts the save and must be re-read and merged, and the response carries id/name/folder/revision. The optimistic-concurrency rule is exactly the kind of behavior an agent cannot infer from annotations or 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?

Four tight sentences, front-loaded with the create-or-update distinction, followed by the mutation rule, the secret rule, the return shape, and the conflict rule in priority order. The framing clause 'so the developer finds it in the Gostman app and it can be re-run later' is slightly narrative but justifies persistence, so it earns its place; nothing is padded.

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?

For a 13-parameter mutation tool with nested assertion/extractor objects, an output schema, and full annotation coverage, the description supplies the remaining essentials: partial-update semantics, secret refusal, and revision-conflict recovery. Everything an agent needs to avoid a failed or destructive save is present without duplicating the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning on top: the id-omitted creation path, the revision staleness rule and its session-default fallback, and the variable-reference requirement for credential-bearing values. It slightly blurs 'only the fields you give are changed' against schema notes that tags/headers/assertions are replaced wholesale, but that ambiguity is minor.

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?

The first sentence states a specific verb and resource with both modes: 'Create a request in the workspace, or update one by id', plus the observable outcome (visible in the Gostman app, re-runnable). It also implicitly separates this from the read path by naming get_request later, so an agent can tell it apart from get_request/send_request without opening a 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?

It gives clear selection rules: omit `id` to create, supply `id` to update, and read with get_request first before updating. Secrets handling is stated as a hard rule rather than a hint. It stops short of naming alternatives for other flows (e.g. bulk import vs. single save), so there is no explicit when-not-to-use.

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