save_assignment_grade

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

Since no annotations are provided, the description carries the full burden of behavioral disclosure. It reveals the safety default of dry-run, specifies the validation behavior, and describes the return format ('JSON with validated status and confirmation'). This goes beyond the schema (which only shows default values) and gives the agent a clear expectation of the tool's side effects. It does not mention permissions or overwrite behavior, but given the dry-run safeguard, the disclosed traits are relevant and reasonably complete.

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 well-structured and efficiently sized. It opens with a one-line purpose, follows with a note on the dry-run behavior, enumerates parameters in a clear list, and ends with the return type. Every sentence earns its place, and the format is easy for an LLM to parse. No redundant or filler content is present.

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 tool has 5 parameters with no schema descriptions and no annotations, yet the description provides a clear purpose, parameter semantics, and usage workflow. It also mentions the output format, which is slightly redundant given the output schema exists but is not harmful. The description is adequate for a save operation, though it could enhance completeness by noting error cases or whether it overwrites existing grades. Overall, it is complete enough for the tool's complexity.

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 description must compensate, and it does comprehensively. It defines all five parameters with meaningful details: assignment_id (instance ID), user_id (student ID), grade (numeric 0-10), feedback (optional text), and dry_run (validate without saving). This adds critical semantics not present in the raw schema, such as the valid grade range and the meaning of the dry_run flag.

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 purpose: 'Save a grade for a student's assignment (TP).' This is a specific verb+resource combination that immediately distinguishes it from sibling read-only tools like list_assignments or get_grades_report. The action is unambiguous and matches the tool name without being tautological.

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 explains the dry-run workflow ('By default runs in dry_run mode. Set dry_run=False to actually save'), which gives useful usage context. However, it does not explicitly mention when to choose this tool over alternatives or when not to use it. Alternatives are not named, so guidance is implied rather than explicit.

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