Explore Learning Options

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

Annotations already establish a read-only, non-destructive, idempotent profile, so the description's job is to add behavior beyond that. It does: the 'tolerates an unavailable study-plan or catalog section and reports partial results in warnings' disclosure is genuinely valuable, since an agent would otherwise misinterpret missing data as a failure. It stops short of describing the warnings format or empty-result 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?

Five dense sentences, front-loaded with the trigger condition and then progressing logically through return payload, failure behavior, parametrization, and follow-up workflow. Every sentence earns its place and there's no filler; it's simply a lot of orchestration context for what is fundamentally a two-optional-param tool.

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 zero-required-param tool with no output schema and no enums, the description covers every key decision point: when to call, what you get, how it degrades, how to parameterize, and what comes next. The only gap is the unspoken boundary with the semantically overlapping siblings, which would complete the orchestration story.

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 coverage is exactly 50% — only electiveGroupIds gets a description, and query has just a default. The description compensates by assigning functional meaning to both: 'browse those categories' for electiveGroupIds and 'thematic text search' for query. Both params are optional strings, so the semantic burden is light, but the description still adds real meaning beyond the schema.

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 ('Explore the catalog') with a clear entry condition ('when the student does not yet know module or LU names') and details the unfiltered return payload (raw study plan, elective-group facets, bookable LU summaries). It stops short of explicitly naming its nearest siblings (search_fuxam, get_study_plan) to draw a boundary, so the differentiation is implied rather than stated.

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?

Opens with the selection condition (student doesn't know names) and closes with a follow-up workflow ('use get_module_details and get_learning_unit_details for the shortlist'), which routes the agent to the right next tool. However, it never explicitly contrasts against search_fuxam or get_study_plan, so the 'when not to use it / use X instead' guidance is absent.

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