post_grades

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals key traits: default is a dry run, requiring dry_run=false to actually write; fix mode is the only mode that deletes a comment and only for the current attempt; and the tool aborts if unread evidence exists. These are critical behaviors beyond the basic write operation, making the tool's runtime behavior clear.

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 concise yet dense, using four well-structured sentences. Each sentence adds unique value: the core purpose, the input requirement, the dry-run behavior, the fix mode caveat, and the abort condition. It is front-loaded and free of waste.

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 essential context: the expected input state (POST-READY, not Stage-A), the default dry-run safety, the fix mode's side-effects, and the abort condition. Since an output schema exists, the absence of return-value details is acceptable. The description is fully sufficient for an agent to select and invoke the tool correctly.

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 input schema provides only names, types, and defaults with 0% description coverage. The description compensates excellently by explaining grades_json as the POST-READY file, dry_run as the default behavior, and fix as the corrective mode for earlier mis-grades, including the deletion constraint. This gives full semantic meaning to all three parameters.

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 function: 'Write the rendered grades and comments to Canvas.' The verb 'write' and resource 'rendered grades and comments' are specific, and 'Its own step, asked for on its own' distinguishes it as a standalone posting step, differentiating it from grading tools like grade or grade-nb.

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 strong usage context: it is a standalone step for posting rendered grades, expects a POST-READY file, and refuses Stage-A files. It also explains the dry-run default and fix mode. However, it does not explicitly name alternative tools or state when NOT to use this tool, so it misses the 'explicit exclusions/alternatives' criterion for a 5.

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