get_internal_totals

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

Despite annotations already covering the read-only/idempotent profile, the description adds substantial behavior: it explains that VTOP omits unpublished components rather than zeroing them, that 'outstanding' does not mean unconducted, that attendanceForecast is a projection paid only after the last instructional day, that grades are relative to class average, and that login is required. This is exactly the kind of domain-specific caveat annotations cannot express.

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 content is dense and front-loaded on the totals concept, but the ordering directive and the inline component arithmetic (40 = 35+5, CAT-I 15 + CAT-II 15, etc.) make it longer than necessary and push operational caveats into a single run-on block. It is information-rich but not tightly structured.

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?

With no output schema, the description carries the return-value burden and does so thoroughly, defining scoredSoFar, percentOfScale, outstanding, and attendanceForecast and explaining the edge cases behind them. An agent has enough to interpret the response and to call the tool correctly with no required parameters.

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 description coverage is 100%, so both parameters are already documented in structured form. The description restates that semesterId is optional and defaults to the current semester, which duplicates the schema rather than adding syntax or format detail. Baseline 3 is appropriate.

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 opens with a specific verb+resource ('TOTAL internal marks for every subject') and pins down the aggregation being performed, which separates it conceptually from raw-mark siblings like get_marks. However, it never names or explicitly differentiates itself from get_marks or get_semester_grades, so the agent must infer which sibling to prefer from context alone.

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?

Usage is only implied: the reader learns the tool returns totals and should order output a certain way, and that semesterId may be omitted. There is no statement of when to call this versus get_marks or get_semester_grades, and no when-not conditions. The 'refresh' trigger lives in the schema, not the description.

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