broker.useRedeems a sealed grant for the bound acting agent and executes the bound action through the Gateway and Policy Engine; does not expose plaintext secrets.
| 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?
No annotations are provided, so the description carries the full burden. It discloses meaningful behavioral traits: execution goes through the Gateway and Policy Engine, and plaintext secrets are not exposed. It does not mention grant consumption, idempotency, or failure modes, but it provides strong behavioral context for a security-sensitive operation.
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 or repetition. Every clause contributes either an operational fact or a security guarantee, and the core action is front-loaded.
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 description covers core behavior and the secret-handling boundary, but it omits usage conditions, what a successful redemption returns, and whether the grant is consumed or reusable. With no output schema and no annotations, slightly more context would be needed for fully confident invocation.
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 at 100%, so the baseline is 3. The description adds some semantic color by implying grant_token is a sealed grant and acting_agent_id is the bound acting agent, but it does not provide format, provenance, or lifecycle details beyond what the field names suggest.
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 names a specific operation ('redeems a sealed grant') and its consequence ('executes the bound action through the Gateway and Policy Engine'). It clearly distinguishes broker.use from sibling tools like introspect-grant, register-credential, request-access, and revoke-grant, which are about lifecycle or inspection rather than consuming a grant.
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 implies when to use it: when you hold a sealed grant and want the bound action to execute for the acting agent. However, it does not explicitly state when to prefer this over alternatives, nor does it mention exclusions or siblings, so the agent has to infer the selection logic.
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.