Get Late Policy

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so 'Read-only' adds nothing. However, 'Returns an error if the course has no late policy' is a genuine behavioral disclosure not present in any structured field, telling the agent to expect a failure mode rather than an empty result. It stops short of describing response shape or the units of the late interval.

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?

Two short sentences, each earning its place: one names the payoffs of calling the tool, the other flags the error condition. The resource is front-loaded and there is no filler.

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?

With no output schema, the description correctly compensates by enumerating the returned fields (deduction percentage, penalty floor, missing-work grade), so an agent knows what it gets back. The only gap is that the late interval's units and the error type/format are unspecified, which is minor for a single-parameter read.

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?

Only one parameter, and the schema fully documents it at 100% coverage, including the numeric-string format and the pointer to list_courses for obtaining it. The description adds no additional parameter detail, so baseline 3 is appropriate when the schema does all the work.

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 opens with a specific verb+resource ('Get a course's late policy') and then enumerates exactly what the policy contains: per-interval deduction, penalty floor, and missing-work grade. That is well beyond a restatement of the name. It does not explicitly distinguish itself from nearby siblings such as get_course_settings or get_grading_standard, which keeps it off a 5.

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?

Usage is only implied: 'course's late policy' makes clear this is course-scoped, and the trailing clause about erroring when no late policy exists gives an agent a useful precondition. There is no explicit when-to-use or when-not-to-use guidance versus alternatives like get_grading_standard, which also carries penalty-type information.

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