refresh_source

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

Annotations already declare this is a non-read-only, non-idempotent, open-world, non-destructive operation, so the safety profile is covered. The description adds genuine behavioral context beyond that: it reports scope and partial failures, and bounds each course fetch to 1–50 records.

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?

A single dense sentence that front-loads the fetch action and packs source list, range limit, failure reporting, and the semester caveat with no filler. The extreme terseness borders on cryptic but nothing is wasted.

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?

An output schema exists, so return values need not be described. Given 3 parameters and no enums in the schema, the description supplies the missing source options, limit bounds, optional-semester behavior, and partial-failure reporting — enough for an agent to call it correctly, though it never says where refreshed data is stored.

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 carries the full burden and does compensate well: it enumerates candidate source values, documents the 1–50 per-course limit, and states that semester may be left empty for 教务 sources. Only the exact meaning of each source token remains unexplained.

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 (按需获取/on-demand fetch) and names the concrete resources it pulls (public/oa/jw/mystu/yuketang), which distinguishes it from the read-only get_* siblings. The individual source tokens are opaque to an outside reader, but the fetch/ingest intent is clear.

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?

'按需' (on demand) implies refresh-style usage rather than scheduled or first-time retrieval, and the semester note hints at a conditional parameter. However, no alternative tool is named and there is no explicit when-not guidance, so usage is only implied.

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