Skip to main content
Glama

Prior Ledger

review_proposal

Reviewer tokens only. Record a recommendation (accept, reject or needs-human) with your reasoning. Use needs-human whenever you are unsure; a steward will decide.

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": {
      "pid": "<pid>",
      "recommendation": "<recommendation>",
      "reasoning": "<reasoning>"
    },
    "name": "review_proposal"
  }
}

Input Schema

NameRequiredDescriptionDefault
pidYes
reasoningYes
recommendationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write-not-destructive profile is covered structurally. The description adds real value beyond that by disclosing the reviewer-token requirement and the downstream consequence that a steward makes the final call. It does not say whether a prior recommendation is overwritten or whether the call is idempotent.

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 short sentences, front-loaded with the access prerequisite, then the action, then the fallback rule. No redundant restatement of the name or title.

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 simple mutation with no output schema and zero schema coverage, the definition covers the auth gate, valid values, and the escalation path, which is most of what an agent needs. Missing pieces are edge behavior: whether re-review is allowed, whether a recommendation can be revised, and what identifier pid refers to.

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 0% and the recommendation parameter is an unconstrained string, so the enumeration of accept/reject/needs-human is essential and is the description's main contribution. However, pid and reasoning receive no clarification at all; pid in particular is unexplained, so compensation for the coverage gap is only partial.

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 specific action: record a recommendation on a proposal, with the allowed recommendation values spelled out. It stops short of distinguishing itself from the sibling accept_proposal/reject_proposal tools, so an agent must infer that this records an opinion rather than enacting a decision.

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?

Gives a clear access condition ("Reviewer tokens only") and a decision rule ("Use needs-human whenever you are unsure; a steward will decide"). It lacks an explicit alternative clause such as "to actually accept the proposal, use accept_proposal," which matters given the sibling names.

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.