run_stage_a

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

With no annotations, the description carries the transparency burden. It discloses key behaviors: returns per-student scores and evidence, posts nothing, writes no comment, and saves artifacts. This adds significant context beyond a generic 'run' description, though it doesn't mention permissions or reversibility.

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 two sentences with a clear lead sentence and a precise clarification. No redundancy; every clause adds information about behavior or return value.

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 the main purpose, return values, and non-actions (no posting, no comments). It lacks parameter details and specifics about artifact storage, but given the tool's complexity, the high-level context is well covered. The absence of an output schema is compensated by the return-value explanation.

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%, and the description does not mention the parameters (course, code, rubric) at all. The agent must infer their meaning from names alone. The description fails to compensate for the lack of schema documentation.

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 clearly states the tool's action: run Stage A to collect submissions, score machine-scorable items, and save artifacts. It also explicitly distinguishes itself by noting it posts nothing and writes no comment, separating it from sibling tools like post_grades.

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 provides clear context: this is the automated scoring stage before Stage B (wording) and before posting, which is a separate authorised step. It implies when to use the tool and when not to, but doesn't explicitly name an alternative tool or provide explicit exclusions.

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