Skip to main content
Glama

ASI.EXPRESS

propose_capability

Idempotent

Propose a new capability as a declarative JSON recipe. Each step names one connector or one catalog entry by id. It is validated; a valid recipe is stored as a public DRAFT only. Nothing is executed. Limited per caller and per day.

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": {
      "recipe": "<recipe>"
    },
    "name": "propose_capability"
  }
}

Input Schema

NameRequiredDescriptionDefault
needNooptional: the need in a few English keywords
recipeYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Adds substantive traits that annotations cannot convey: the recipe is validated before storage, a valid result becomes a PUBLIC draft (visibility consequence an agent must know before submitting content), nothing is executed, and calls are rate-limited per caller and per day. The idempotentHint/destructiveHint flags are consistent with 'stored as a draft only, nothing executed,' so no contradiction.

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?

Five short sentences, front-loaded with purpose, then constraints, then side effects, then rate limits. No filler or repetition; each sentence contributes a fact an agent needs.

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?

Strong coverage for a nested, mutating tool: validation, draft visibility, non-execution, and rate limits are all disclosed, and the output schema can carry the validation-result format. The remaining shortfall is authoring guidance for `test_cases` and `need`, which an agent may otherwise omit or misuse.

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?

The sentence 'Each step names one connector or one catalog entry by id' adds a real constraint beyond the schema: the connector/entry/op/tool fields are mutually exclusive per step, which the nested schema does not state. However, the description says nothing about the `need` field, the `test_cases` array, or the fact that `params` values accept literal, {input}, {step}, and {calc} forms — leaving gaps at 50% schema coverage.

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 specific verb and resource ('Propose a new capability') plus the artifact form ('declarative JSON recipe'), and the line 'Nothing is executed' implicitly separates it from run_capability and get_capability. An agent can tell this is a create-a-definition operation, not an execution or lookup, without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives useful context — validated, stored as draft, nothing executed — which implies the use case of authoring rather than running. But it never explicitly says when to pick this over suggest_capability (which presumably helps compose one) or when to fall back to run_capability once a draft exists; the routing is left to inference.

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