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

With no annotations, the description carries the full burden. It discloses that rooms may be null when not yet published, and implies a read-only operation. It does not cover authentication needs or rate limits, but the behavioral traits relevant to invocation are adequately described.

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 three sentences: one detailing the tool's output, one summarizing the use case, and one covering edge cases (room publication date, year omission). Every sentence adds essential information with no redundancy.

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?

Given the absence of an output schema, the description effectively enumerates return fields (date, start time, duration, aids code, system, rooms) and notes null behavior for rooms. It is complete enough for the tool's complexity, though it does not address error handling or input validation.

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 0%, so the description must compensate. It clarifies that 'course_codes' are for NTNU courses (array of strings) and that 'year' can be omitted for the current year. However, the 'language' parameter is not mentioned, leaving its intent undocumented. The description adds moderate value 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?

The description clearly states the tool retrieves exam logistics for one or more NTNU courses, listing specific fields (date, start time, duration, aids code, rooms). It distinguishes itself from sibling tools like get_course_info by focusing exclusively on exam details and answering a specific user question ('when and where are my exams and what can I bring').

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 provides practical usage guidance: it can handle multiple courses in a single call, advises omitting year for the current study year, and explains that rooms are only published days before (unpublished fields are null). However, it does not explicitly contrast with sibling tools or state when not to use this tool.

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