Execute reviewed exam questions from an owned queue while enforcing a step limit and stopping new steps after 20 seconds to avoid overrun.
Execute reviewed questions; stop starting new steps after 20 seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| max_steps | No |
Changes observed during successful MCP inspections.
v1.9.4Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden; it does disclose one real behavioral trait — it stops starting new steps after 20 seconds — which is genuinely useful. However, it never states that this is a state-changing execution loop, whether it can be interrupted, what happens to steps it did not start, or how failures surface.
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?
A single compact sentence with the action front-loaded and the time bound appended. No waste, but the terseness contributes to the specification gaps rather than being purely efficient.
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?
For an execution loop with no annotations, no output schema, and an undocumented parameter, the description leaves too much unknown: return values, progress reporting, idempotency, and interaction with exam_loop_progress are all unaddressed.
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?
The single parameter max_steps has 0% schema description coverage and defaults to 6, yet the description says nothing about it — not what a 'step' is, nor that the 20-second cut-off limits how many steps actually run. The description fails to compensate for the coverage gap.
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 verb 'Execute' with object 'reviewed questions' gives a rough sense of the action, but the tool name references a queue while the description never mentions a queue, ordering, or what a 'reviewed question' is in this domain. It does not distinguish itself from nearby siblings such as run_exam_question_loop or exam_loop_progress.
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?
There is no statement of when this should be invoked versus alternatives, no prerequisites (must questions be reviewed/staged first via stage_owned_exam_reviews?), and no indication of what happens on timeout. The 20-second note is a behavior, not usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.