Archive: Search Courses

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

Annotations already establish readOnly, idempotent, openWorld and non-destructive behavior, so the description rightly focuses on the archive-wide scope ('every term it has ever seen'), which is genuine behavioral context. It stops short of describing result shape or result-count behavior, but the output schema covers that.

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 tight sentences: the first front-loads what it does and its scope, the second gives the routing guidance. 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?

Purpose, scope and usage are fully covered, safety is handled by annotations, and a return schema exists so return values need no explanation. The only shortfall is silence on the limit/pagination parameter, which matters for a default-20 search tool.

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?

With 0% schema description coverage the description must carry the param burden; it clarifies that the query accepts a code OR a name fragment, which is meaningful beyond the bare 'string' type, but it never mentions the 'limit' parameter or its default of 20.

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 (search) and resource (the archive's full course index) and scopes it precisely to 'across every term it has ever seen — not just the active one,' which cleanly separates it from the sibling active-term searches like list_courses and obs_search_courses.

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?

Explicitly names the situation to use it ('to find the exact code archive_course_history needs when only a name fragment is known') and names the sibling it feeds, giving the agent a concrete triggering condition and routing.

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