pull_exam_set

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

With no annotations present, the description carries the full burden, and it does disclose important failure behavior (a mismatch with summaries raises an error instead of returning incomplete data) plus pagination (limit=0 means all) and truncation via max_content_chars. It does not state whether the call is read-only, whether it requires an active pta_login session, or anything about rate limits, which matters for an unannotated tool.

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 scoping and error-guarantee sentence is front-loaded, then a tight Args list. Every line carries information, though the overall block is longer than strictly needed and could fold offset/limit into a single line.

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 six-parameter, no-annotation, no-output-schema tool, the description covers what each mode returns (id/type/title vs. stem with the first line as title), paging, truncation, and the failure mode. The only material gap is the absent authentication/session prerequisite and confirmation that the operation is non-destructive.

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 0%, so the description must compensate entirely, and it does: every one of the six parameters is explained, including the three undocumented mode values with their distinct return content, the limit=0 sentinel, the digest-specific 15–30 recommendation, and the default-ish role of max_content_chars.

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 opening states a specific verb+resource: fetch problems from an exam set filtered by problem type, with a summaries cross-check that errors out rather than returning partial data. It is clearly distinguishable from pta_list_exams (which supplies the problem_set_id) and from submit_answers, though it never names a sibling outright.

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?

It gives concrete selection guidance: problem_set_id comes from pta_list_exams, and mode is explained as a choice with explicit consequences (index = overview, digest = stem only, content = longer stem). It also recommends limit 15–30 for digest. What's missing is any statement of when not to use this tool versus submit_answers or pta_submission_detail.

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