Skip to main content
Glama
Sign In
Kiln

Kiln

by codeofaxel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

retrieve_credential

Destructive

Decrypt and return a stored credential by its unique ID to provide authenticated access to protected resources.

Instructions

Decrypt and return a stored credential.

        Args:
            credential_id: The credential's unique identifier.

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": {
      "credential_id": "<credential_id>"
    },
    "name": "retrieve_credential"
  }
}

Input Schema

NameRequiredDescriptionDefault
credential_idYesThe credential's unique identifier.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.5.1
    • addedInput schema / properties / credential_id / description
      Added value: +"The credential's unique identifier."
  2. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already flag readOnlyHint=false and destructiveHint=true, and the description usefully explains why: the stored value is decrypted and returned in plaintext, i.e. a secret is exposed. That is genuine added context. But it says nothing about authorization requirements, audit logging, or whether the plaintext is cached/rate-limited, which matters for a secret-reveal operation and would push this to a 4 or 5.

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?

The operative sentence is front-loaded and wastes no words. The docstring-style 'Args' block is pure duplication of the schema and could be dropped, but it is short enough not to obstruct reading.

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

Completeness3/5

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

The tool is simple (one required param, no output schema, no nested objects) and the annotations carry the risk profile, so the definition is minimally sufficient. It still omits the return shape (raw string vs. structured object, encoding) and any security/authorization context expected of a credential-reveal tool.

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% and the single parameter is fully documented in the schema; the 'Args' block merely restates 'The credential's unique identifier' verbatim. No extra meaning (format, where to obtain the ID, error behavior for unknown IDs) is added, so the baseline of 3 applies.

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?

The description names a specific verb pair and resource: 'Decrypt and return a stored credential.' An agent knows exactly what comes back (a decrypted secret) and for which entity. It does not, however, mention the obvious siblings store_credential / list_credentials to make the boundary explicit, so it falls short of a 5.

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?

There is no when-to-use guidance at all: nothing says to call list_credentials first to find an ID, nothing distinguishes this from list_credentials (which presumably does not decrypt), and there are no prerequisites or exclusions. The agent must infer usage entirely from the name.

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

Deploy Server

Other Tools