Skip to main content
Glama

Boundra — Payment Approval Gateway for AI Agents

set_policy

[USER ONLY] Submit a new policy version. Must carry the user's wallet EIP-191 signature over the policy document; accepted only after signature + version-chain checks pass. Agents MUST NOT call this tool.

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": {
      "owner": "<owner>",
      "scope": "<scope>",
      "version": "<version>",
      "nl_rule": "<nl_rule>",
      "prev_hash": "<prev_hash>",
      "created_at": "<created_at>",
      "signature": "<signature>"
    },
    "name": "set_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
ownerYesOwner wallet address that scopes policy, budget and audit state
scopeYesPolicy scope: user for the owner default or agent for one agent
nl_ruleYesNatural-language spending rule to compile and enforce
versionYesMonotonically increasing policy version number
agent_idNoOptional agent identifier for agent-scoped policy or attribution
prev_hashYesPrevious policy hash, or 64 zero characters for a genesis policy
signatureYesOwner wallet EIP-191 signature over the policy document
created_atYesPolicy creation time as a Unix timestamp in seconds

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changed
    • addedInput schema / properties / agent_id / description
      Added value: +"Optional agent identifier for agent-scoped policy or attribution"
    • addedInput schema / properties / created_at / description
      Added value: +"Policy creation time as a Unix timestamp in seconds"
    • addedInput schema / properties / nl_rule / description
      Added value: +"Natural-language spending rule to compile and enforce"
    • addedInput schema / properties / owner / description
      Added value: +"Owner wallet address that scopes policy, budget and audit state"
    • addedInput schema / properties / prev_hash / description
      Added value: +"Previous policy hash, or 64 zero characters for a genesis policy"
    • addedInput schema / properties / scope / description
      Added value: +"Policy scope: user for the owner default or agent for one agent"
    • addedInput schema / properties / signature / description
      Added value: +"Owner wallet EIP-191 signature over the policy document"
    • addedInput schema / properties / version / description
      Added value: +"Monotonically increasing policy version number"
  2. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only tell the agent this is a non-read-only, non-idempotent, non-destructive write. The description adds real context beyond that: a signature is mandatory, and acceptance is gated on signature plus version-chain validation, implying append-only versioned state rather than overwriting. It does not say what an agent receives when validation fails.

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 caller restriction and the purpose; every clause (signature requirement, validation gate, agent prohibition) carries decision-relevant information with 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?

With an output schema, annotations, and full schema coverage, the description only needs to convey who may call it and the validation gate, both of which it does. The remaining gap is failure behavior and whether a rejected submission is retryable, which is minor given the output schema exists.

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 every parameter is already documented, giving a baseline of 3. The description reinforces that 'signature' is the user's own wallet signature over the policy document and that 'prev_hash'/version form the version chain, but adds no format or edge-case detail beyond the schema.

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 ('Submit a new policy version') plus the key precondition (owner wallet EIP-191 signature). Combined with the '[USER ONLY]' tag it is clearly distinguishable from read-side siblings like get_policy and get_policy_versions.

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 an unusually explicit exclusion: '[USER ONLY]' and 'Agents MUST NOT call this tool', which is exactly the routing info an agent needs. It does not name the sibling an agent should use instead (e.g. request_policy_change), so the alternative route is left to inference.

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.