Skip to main content
Glama

Physical Capability Cloud

execute_composition

Commit a proposed composition: drives the DAG through the workflow engine, each step records a reputation outcome, the composition's reputation is finalized when the run ends. When PCC_COMPOSE_EXECUTE_REAL=true is set on the gateway, steps submit real jobs via JobFacade and the workflow run is durable (@pcc/workflow). When the flag is off, the NOOP runner returns synthetic success — useful in dev/test. Re-executing an already-run composition replays the stored result (idempotent — reputation deltas are applied exactly once).

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": {
      "id": "<id>"
    },
    "name": "execute_composition"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesComposition id from propose_composition. Must be in `proposed` status and not expired.
idempotencyKeyNoOptional string, 1-120 characters. The gateway validates it but doesn't use it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / idempotencyKey / description
      Previous value: -"Optional caller-supplied key (≤120 chars) to dedupe execute calls."New value: +"Optional string, 1-120 characters. The gateway validates it but doesn't use it."
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare only non-read-only, non-destructive, so the description carries most of the burden and delivers: it discloses the DAG execution model, per-step reputation writes, finalization at run end, the PCC_COMPOSE_EXECUTE_REAL gate switching between real JobFacade jobs and synthetic NOOP success, and idempotent replay of stored results. The main gap is that it does not describe permissions/auth requirements or failure/error behavior for invalid or expired compositions.

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 sentences, each front-loading the most decision-relevant fact first: what happens, the real-vs-NOOP flag, then idempotency. Dense and free of filler, though the environment-variable and package-name detail is heavier than strictly needed for tool selection.

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 mutation tool with no output schema and minimal annotations, the description supplies the side effects, the environment-dependent execution mode, and the idempotency contract. Missing pieces are return shape and the precondition/error surface, which are only partially covered by schema field text.

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%, so the schema already documents both `id` and `idempotencyKey`, including the odd caveat that the key is validated but unused. The description adds only indirect meaning by framing execution as idempotent with reputation deltas applied exactly once, which helps the agent reason about the key but does not document either parameter directly.

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 ('Commit a proposed composition') and immediately elaborates the effect: the DAG is driven through the workflow engine, steps record reputation outcomes, and the composition's reputation is finalized at run end. This clearly differentiates it from sibling read/propose tools like get_composition and propose_composition without needing to open 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 Guidelines3/5

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

Usage context is implied rather than stated: the environment-flag discussion tells the agent when real jobs run versus synthetic NOOP success (dev/test), and the replay note tells the agent that re-invocation is safe. However, it never explicitly says this must follow propose_composition or what precondition failures look like; the 'proposed status and not expired' requirement lives only in the schema, not the description.

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.