check_task_access

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

With no annotations, the description carries full behavioral disclosure, and it provides meaningful details: it appends an audit record, denial wins over allowance, high-risk actions require approval, and it fails closed on audit failure. It stops short of fully describing the return status or auth model, so not a 5.

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?

Three tight sentences deliver a surprising amount of crucial behavior: side effect, decision logic, approval requirements, and fail-closed behavior. There is no filler or redundant restating of the schema.

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 is robust on side effects and policy behavior, but without an output schema it omits the return value and approval flow details. It also fails to clarify the 'approvals' input and how 'requires approval' manifests in the response, leaving a material gap for a decision tool.

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 0%, so the burden is on the description to explain parameters. The description only names action, resource, and reason, and only vaguely references the approvals parameter. Agent, projectId, taskId, and approvals array semantics are left unexplained, which is a significant gap for a 7-parameter tool.

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?

Clearly states it evaluates a task-scoped access request and appends an allow or deny record, so an agent can see this is an audit/write action despite the 'check' name. The WRITE/AUDIT prefix and the specific resource ('task-scoped access request') separate it from read-only sibling tools like get_task_security.

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 a task-scoped access request needs evaluation and auditing. It states required inputs and approval conditions, but it does not explicitly say when not to use it or name any alternatives, leaving sibling differentiation to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.