intentfence_authorize_actionAuthorize an exact agent action against an explicit allowlist, spend ceiling, retention ceiling, and optional action-bound approval. Returns a five-minute ES256 receipt and never executes the downstream action. Callers must verify the receipt and fail closed if the action changes.
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | ||
| policy | Yes | ||
| context | No | ||
| subject | Yes | ||
| approval | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark readOnlyHint=true, so the description adds value by stating 'never executes the downstream action' and revealing the receipt validity (five-minute ES256). It also implies the tool is safe for repeated calls (no side effects). No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences with no redundant phrasing. It front-loads the core purpose and immediately follows with critical behavioral constraints. Every sentence adds unique value without repeating schema or annotations.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 params, nested objects, no output schema), the description covers the tool's purpose, key constraints, and post-call verification. It lacks explicit output structure, but the mention of a 'five-minute ES256 receipt' implies a signed token, which may suffice for agents. The instructions to 'fail closed' add practical completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It provides high-level mapping: 'exact agent action' (action param), 'explicit allowlist, spend ceiling, retention ceiling' (policy param), and 'optional action-bound approval' (approval param). However, it omits explanation of subject and context parameters, and the nested action structure is not detailed. This is adequate but incomplete.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses specific verbs ('authorize an exact agent action') and clearly identifies the resource being operated on (allowlist, spend ceiling, retention ceiling). It distinguishes itself from sibling tools like intentfence_agent_risk_scan and intentfence_preflight by emphasizing authorization against explicit policies rather than risk assessment.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the tool never executes the downstream action and provides clear post-call instructions: callers must verify the receipt and fail closed if the action changes. This tells agents exactly when and how to use this tool (before execution) and what to do with its output.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose, from risk scanning to authorization, preflight checks, and specific data retrieval. Descriptions are detailed and non-overlapping.
All tools follow a consistent 'intentfence_<descriptive_name>' pattern with snake_case, making them predictable and easy to distinguish.
10 tools is well-scoped for a security firewall server, covering a range of free and paid services without being overwhelming or too sparse.
The set covers assessment, authorization, and data retrieval, but lacks tools for managing the firewall configuration itself (e.g., allowlist CRUD), leaving some gaps in lifecycle coverage.