broker.request-accessAsks the canonical Policy Engine for an ALLOW decision before issuing a short-lived HMAC-sealed grant bound to credential, mandate, agent, scope, and expiry.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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?
With no annotations provided, the description carries the full behavioral burden. It does disclose the core behavior: consulting the Policy Engine, requiring an ALLOW decision, and issuing a short-lived sealed grant. It does not disclose expected failure/denial behavior, whether this creates a persistent record, or what caller permissions are needed, which matters for a security-sensitive grant issuance tool.
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 a single, dense sentence with no filler. The most important behavior—policy-engine evaluation before issuance—is front-loaded, and every phrase carries meaning.
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?
The tool has no output schema and no annotations, and it involves a nontrivial authorization flow. The description communicates the essential purpose and grant constraints, but omits useful operational context such as what happens on denial, response shape, or prerequisites. It is adequate but not rich enough to fully guide an agent without additional inference.
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 description coverage is reported as 100%, so the baseline is 3. The description adds some semantic binding context—credential, mandate, agent, scope, and expiry—which maps roughly to the required parameters, but it does not clearly map 'action' to a specific grant scope or clarify how expiry is determined.
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 states a specific verb ('Asks... for an ALLOW decision before issuing') and names the exact resource ('short-lived HMAC-sealed grant') along with its binding attributes. This clearly distinguishes broker.request-access from siblings like broker.revoke-grant, broker.introspect-grant, or broker.use.
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?
Usage is implied: the tool is for requesting access before a grant is issued, and the policy-engine phrasing suggests it is a prerequisite step. However, it does not explicitly state when to choose this over sibling tools, nor does it mention scenarios where it should not be used or what alternative may be more appropriate.
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.
Most tools target distinct resources and actions, but broker.request-access and mandate.authorize-action both route through the Policy Engine and could be confused for the same intent. broker.revoke-grant and mandate.revoke are distinct in scope but similar in naming; descriptions mostly resolve the ambiguity.
The domain-prefixed verb_noun pattern is mostly consistent, e.g. broker.register-credential, broker.revoke-grant, mandate.authorize-action. Minor deviations like broker.use and mandate.revoke are less explicit about their object, but they remain readable and predictable.
Eleven tools is well-scoped for a credential/mandate broker, covering issuance, delegation, access, revocation, and proof without redundancy. Each tool appears to earn its place in the workflow.
The core mandate lifecycle (mint, delegate, revoke) and grant flow (register, request, use, introspect, revoke) are covered, with no immediate dead ends. However, there is no query/list/status tool for existing mandates or credentials, and credential management lacks removal or rotation operations, which creates notable gaps for state discovery.