Skip to main content
Glama

Panel: save what the user typed

save_secret
Destructive

Stores a user-provided secret for a pending request so the app can use it while keeping the secret, tool input, and result hidden from the AI model.

Instructions

The panel's form sends what the user typed (a database password, the sharing code) for the ask in its _meta (or read with secret_request). App-only: the model never sees this tool, its input or result.

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": {
      "request": "<request>",
      "secret": "<secret>"
    },
    "name": "save_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
secretYes
requestYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds useful context that the payload is user-entered secret material that never surfaces to the model. However, it does not explain what the destructive semantics mean for the stored value — whether an existing secret is overwritten, retained, or how long it persists — which is exactly the behavior an annotation cannot convey.

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?

Two tightly packed sentences with no filler, and the critical 'App-only / model never sees this' clause arrives early enough to stop a model from attempting a call. Slight density comes at the cost of clarity in the _meta phrasing.

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 two-parameter internal tool with no output schema, this covers what matters: who invokes it, where the request originates, what the secret is, and that results are not returned to the model. The remaining gap is post-save lifecycle of the secret, which is minor given the tool is explicitly out of the model's reach.

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 0%, so the description carries the parameter burden. It does gloss both parameters: secret = what the user typed (database password, sharing code) and request = the ask carried in _meta. But 'the ask in its _meta' is cryptic about format and origin, leaving real ambiguity for a caller that supposedly never sees 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 the concrete action — the panel form submits user-typed values (a database password, the sharing code) tied to the request in the ask's _meta — and points to the sibling secret_request for the read path. It is specific enough to distinguish from siblings, though the verb 'save' itself is only implied by the tool name/title rather than stated.

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?

Explicitly says this is App-only and that 'the model never sees this tool, its input or result', which is a clear when-not-to-use signal for any agent. It also names secret_request as the read counterpart, so the read-vs-write split is unambiguous.

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