get_categories

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does not state whether institution is a filter or free-form, whether results are paginated, what the output structure looks like, or any side effects. Given there's no destructive/write risk here (it's a list operation), the main gap is lack of detail on output contents and filtering behavior.

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 exceptionally short (one clause) with zero wasted words. However, this is under-specification rather than genuine conciseness — the brevity comes at the cost of the clarity dimensions. There's nothing unclearly phrased, but there's also almost nothing there.

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?

While the tool has an output schema (which helps) and only 1 optional parameter, the description leaves too much ambiguous: what categories vs levels mean, how institution affects results, and how this relates to the 9 sibling tools exploring the same course domain. For an exploratory/list tool in a crowded sibling space, this level of terseness is inadequate.

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?

The schema has 1 optional parameter (institution) with 0% description coverage and no enums. The description fails to explain what institution does — is it a filter, a scoping operand, or optional context? The schema shows it defaults to null, but the description provides zero guidance on how to populate it or what difference it makes to results. With an optional string param, the agent needs to know if it's required for meaningful results.

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 'List course categories/levels' gives a verb+resource but is vague about what 'categories/levels' actually means in this system. With siblings like list_faculties, list_course_types, and get_course_structure, it's unclear how categories/levels differ from course_types or the structure/faculty dimensions. The ambiguity between 'categories' and 'levels' (slash suggests they may be synonyms or distinct concepts) makes the purpose unclear and fails to distinguish from siblings.

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?

No guidance is given on when to use this tool vs alternatives like list_course_types or list_faculties. The semantic overlap with list_course_types ('categories' vs 'types') is significant and undocumented. No context about whether this is a top-level navigation call or whether it should be filtered by institution, or what prerequisites apply.

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