mcp-server

Evaluate Approval Policy

alterlab_policy_evaluate

Read-onlyIdempotent

Show what the signed-in user's approval policy would decide for a planned batch of actions: auto (runs without asking), ask (needs the user's approval) or deny (refused), with the rule ids and reasons. Nothing runs and no limit is used. Use before alterlab_task_act to know whether the batch will pause for approval. Pass the domains, the actions and, per action, its risk class; an action without a class is treated as submit. This tool cannot create or change policies: the user does that in the dashboard.

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": {
      "domains": "<domains>",
      "actions": "<actions>"
    },
    "name": "alterlab_policy_evaluate"
  }
}

Input Schema

Name	Required	Description
`amount`	No	Amount the batch commits, in major units of currency
`recipe`	No
`actions`	Yes	The planned browser actions, as for alterlab_task_act
`domains`	Yes	Sites the actions run on
`currency`	No
`task_label`	No
`risk_classes`	No	Risk class per action: navigate, input, draft, submit, message, money, legal_attestation or human_only
`facts_verified`	No	How many written values are backed by verified facts. Default none
`counterparty_class`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds context beyond the readOnly/idempotent annotations: 'Nothing runs and no limit is used' reassures the agent that a hypothetical evaluation consumes no quota, and the dashboard note clarifies the write boundary. It does not describe latency or how unknown domains/classes are handled beyond the 'submit' default, so not a full 5.

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?

Four short sentences, each doing work: what it returns, its side-effect profile, when to call it and with what, and what it cannot do. The key routing instruction is front-loaded and there is no filler.

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, no-output-schema tool, the description covers the return value (decision plus rule ids and reasons) and the core inputs, which is most of what an agent needs. The gap is that monetary and attribution parameters (amount, currency, counterparty_class, task_label) are never related to the policy evaluation, leaving ambiguity about whether they affect the verdict.

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?

At 56% schema coverage the description compensates partially: it says to pass domains, actions and a risk class per action, and adds a default not stated in the schema ('an action without a class is treated as submit'). However amount, currency, recipe, task_label, counterparty_class and facts_verified go unmentioned, even though amount/currency plausibly influence money-related policy decisions.

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 ('Show what the signed-in user's approval policy would decide') plus the exact output shape (auto/ask/deny with rule ids and reasons). This clearly separates it from alterlab_run_approve (which acts on approvals) and alterlab_task_act (which executes).

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

Usage Guidelines5/5

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

Explicitly names the sequencing: 'Use before alterlab_task_act to know whether the batch will pause for approval', and states the exclusion that the tool cannot create or change policies (that happens in the dashboard). The agent knows both when to call it and what it cannot do.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.