permission_checkEvaluate whether a subject can perform an action on a resource, letting callers inspect their own RBAC permissions or check another subject with admin read access.
Evaluate an authorization tuple
A caller can inspect its own permissions. Evaluating another subject requires administrative rbac read authorization.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes |
Changes observed during successful MCP inspections.
v0.4.3Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description's real contribution is the authorization requirement for cross-subject evaluation, which is genuinely useful. It never states the outcome form (an allow/deny decision) or whether an unauthorized check returns an error versus a denial, which leaves a behavioral gap beyond the 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?
Two sentences, no filler, and the self/other-subject constraint is front-loaded. The only waste is the first line echoing the title rather than using that space to explain the operation.
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?
With no output schema, the description carries the burden of explaining what comes back, yet it never says whether the result is a boolean decision, an error, or an effect list. For an evaluation/decision tool with a nested request object and a wildcard action, the absence of result semantics and object-format expectations is a notable gap.
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?
There is one top-level parameter (`body`) wrapping a nested CanRequest, and schema description coverage is 0% apart from the `subject` property, which already carries the exact statement about rbac read permission. The description therefore duplicates the one documented field and adds nothing about `resource`, `action` (including the `*` wildcard), or `object` format.
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 opens by restating the title verbatim ("Evaluate an authorization tuple") and never explains in plain terms that the tool answers whether a given subject may perform an action on an object. The second sentence does add scope (self-check vs. other-subject check), but the core operation stays framed in opaque jargon that isn't disambiguated from sibling tools like `check`-style or `rbac_*` tools.
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?
It gives one useful context cue: a caller can check its own permissions, and checking another subject requires 'rbac read' authorization. That is a permission prerequisite rather than selection guidance; there is no statement of when to use this versus related tools like `rbac_*` or any allow/deny-tool alternative, but the caller-vs-subject distinction does orient an agent's choice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.