list_courses

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

The description indicates read-only listing behavior and describes available filters, but no annotations are present to cover safety or side effects.It does not discuss response scope, optionality of filters, pagination, or whether results are course-level summaries. Still, 'List' and the filter description give a reasonable core behavioral picture.

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, front-loaded sentences: the first states the core behavior and the second states the filters. The partner examples add genuine value without redundancy. Every sentence earns its place.

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?

For a simple list/filter tool with an output schema and three self-describing filters, the description gives enough to call it correctly. It lacks explicit differentiation from search_course_content and does not state default behavior when no filters are supplied, but these are minor gaps given the simple scope.

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 compensates well by mapping each parameter: query = keyword search, partner = partner organization with concrete examples, topic = topic. It does not specify null handling/case sensitivity or whether filters combine, but it conveys the essential meaning of every parameter.

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 states a specific verb ('List') and resource ('available Short Courses from DeepLearning.AI') and explains the filtering dimensions. This clearly identifies the tool's catalog-level purpose and distinguishes it from the content- and lesson-level sibling tools such as search_course_content.

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 clearly implies a listing/filtering usage: list all available courses or filter by keyword, partner, or topic. However, it provides no explicit when-not-to-use guidance and does not name any sibling tools as alternatives, so an agent must infer that content-level search belongs to search_course_content or get_lesson_* tools.

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