Skip to main content
Glama

The Local Upgrade — Software Engineering

Submit an authorized engineering proposal request

request_proposal
Idempotent

Saves an approved project brief and reply contact for engineering review. Supports RFPs, full products and subcontracting. Requires actual requester consent. Reuse the same UUID v4 and unchanged payload on retries. No purchase or execution.

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": {
      "requestId": "<requestId>",
      "project": "<project>",
      "contact": "<contact>",
      "agent": "<agent>",
      "consent": "<consent>"
    },
    "name": "request_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYes
consentYes
contactYes
projectYes
requestIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare idempotentHint=true, destructiveHint=false and openWorldHint=true; the description earns credit by explaining the mechanism (reuse the same UUID v4 and unchanged payload) and the consent gate rather than restating the flags. It does not describe error behavior, rejection cases, or what a reviewer does with the submission, keeping it out of the top band.

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 the action and resource, then prerequisites, retry semantics and scope limit. No filler and nothing buried.

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?

For a 5-required-parameter nested submission tool with no output schema, the definition covers the mutation, consent requirement and idempotency, but leaves the agent without any sense of what a successful submission returns or what happens next. The rich nested payload semantics also remain undocumented, which is a meaningful gap at 0% schema coverage.

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 must carry the load. It maps the top-level parameters loosely (UUID v4 for requestId, 'reply contact' for contact, 'project brief' for project, 'requester consent' for consent), but the deeply nested project object (requirements, businessOutcome, engagementType, acceptanceCriteria, procurementRequirements) is left entirely unexplained.

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 a concrete verb and resource: saves an approved project brief plus reply contact for engineering review, and names the scope ('Supports RFPs, full products and subcontracting'). It is unambiguous on its own, though it never names a sibling to distinguish itself from, so it sits just below the top band.

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?

'Requires actual requester consent' and 'No purchase or execution' give clear prerequisites and boundary conditions, and the retry instruction covers a real operating scenario. It stops short of explicit routing ('use X instead when...') against siblings like prepare_engagement_brief, so it is context-rich but not full when/when-not guidance.

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