Skip to main content
Glama

Physical Capability Cloud

propose_composition

Propose a composition — a sequenced DAG of capability instances to satisfy a multi-step outcome under a budget + assurance tier. Accepts either a flat steps list or an outcome chain. Returns a candidate plan ranked by optimizeFor (price | speed | quality) with per-step assignments. The composition is persisted for ~30 minutes (proposed status) and can be executed once via execute_composition.

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": {
      "outcomeType": "<outcomeType>",
      "budgetUSD": "<budgetUSD>",
      "minAssuranceTier": "<minAssuranceTier>"
    },
    "name": "propose_composition"
  }
}

Input Schema

NameRequiredDescriptionDefault
stepsNoOrdered list of capability types this composition needs (1..20). Use this OR `outcomeChain`.
locationNoGeographic constraint: lat and lng (both required) and an optional radiusKm.
budgetUSDYesTotal budget the user is willing to spend across all steps.
requesterNo{agentId, did?} — the agent submitting the request.
descriptionNoFree-form natural-language description (≤4000 chars).
optimizeForNoRanking objective (default `price`).
outcomeTypeYesHigh-level outcome label, ≤120 chars. Example: 'desk-robot-prototype'.
outcomeChainNoAlternative to `steps`: a chain of named sub-outcomes. The planner uses only the last entry, as the outcome type to plan for.
minAssuranceTierYesMinimum acceptable assurance tier on every step.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / location / description
      Previous value: -"Geographic constraint (lat/lng + radius, or country, etc)."New value: +"Geographic constraint: lat and lng (both required) and an optional radiusKm."
    • changedInput schema / properties / outcomeChain / description
      Previous value: -"Alternative to `steps`: chain of named sub-outcomes. The planner expands each into capability types."New value: +"Alternative to `steps`: a chain of named sub-outcomes. The planner uses only the last entry, as the outcome type to plan for."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes well beyond them by disclosing that the composition is persisted for ~30 minutes in proposed status and may be executed exactly once. That non-obvious lifecycle, expiry, and single-execution constraint is exactly the 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.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences, front-loaded with the core verb-resource-purpose, then input modes, then return shape, then lifecycle. No filler and no redundancy.

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 9-parameter planning tool with no output schema, the description covers purpose, input modes, return content, and persistence/expiry. It does not address edge behavior such as what happens when the budget cannot satisfy the requested tier, which would complete the picture.

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 description coverage is 100%, so baseline is 3, and the description adds genuine selection meaning by restating that `steps` and `outcomeChain` are alternatives and that ranking is driven by `optimizeFor` (price | speed | quality) with per-step assignments returned. It reinforces the key branching decision rather than merely repeating field names.

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 composition — a sequenced DAG of capability instances') plus the constraint envelope (budget + assurance tier). It also implicitly separates itself from execute_composition by framing the output as a candidate plan to be executed later.

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?

Usage context is clear: multi-step outcomes that need to be planned under a budget and minimum assurance tier, with an explicit either/or input mode (flat `steps` list or outcome chain). It names execute_composition as the follow-up step, though it stops short of an explicit 'call this before X' sequencing statement or exclusions.

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.