Watch Course Sections

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

Goes well past the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false) by disclosing that no login is needed, that at most 20 sections can be watched, that the term is stored because CRNs are reused across terms, that the server cannot run in the background and never notifies, and that seats are only read at check time.

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 core action and the CRN handling lead, and the constraint sentences (20-section cap, no background monitoring) each carry distinct information. It runs slightly long relative to a three-parameter tool, but no sentence is 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 an output schema present, return values need not be described, and the description covers the important operational limits, the fallback pathway, and the term-persistence caveat. The remaining gap is the unexplained program_type parameter, which an agent could easily set incorrectly.

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 schema has three bare parameters, so the description must carry the load. It explains crns (looked up by CRN, term persisted) and department_code (looked up in that department's public OBS schedule), but program_type is never mentioned anywhere, leaving one parameter's semantics fully undocumented.

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?

States a specific verb and resource: 'Add course sections to a local seat watch list by CRN.' It immediately names the downstream sibling (check_watched_course_sections) and the mechanism, so an agent can distinguish it from unwatch_course_sections and list_watched_course_sections without opening any schema.

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?

Gives explicit branching guidance for the optional parameter ('With department_code ... Without it ...'), states the precondition for the fallback path (archive current term must match OBS's serving term), names the follow-up tool, and explicitly rules out the misuse case: 'This does not start any monitoring.'

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