unw_roadmap

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

With no annotations, the description carries the full disclosure burden. It does well on output semantics (prerequisite carry-forward, catalog-gap reporting, graduation-risk notes, and the fact that draft constraints are not applied), but it never says whether the tool is a pure computation or persists/refreshes state, and the 'refresh' parameter hints at caching behavior that is left entirely unexplained.

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?

Dense and front-loaded, with the alternative-tool routing placed last so it doesn't bury the main purpose. The opening parenthetical is the one genuinely wasteful and confusing clause, since it introduces a default without saying which parameter it belongs to.

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 tool with no output schema, no annotations, and five undocumented parameters, the description does meaningful work by describing the shape of the result: term by term requirements, catalog gaps, and risk flags. It still leaves the side-effect model and three parameters unspecified, which is a real gap given the total absence of structured metadata.

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% across five parameters, so the description must compensate. It explains include_summer and gestures at start_term's length behavior, but 'terms', 'refresh', and 'max_credits' get no treatment at all, and the parenthetical about the default reads ambiguously as though it described start_term rather than the term count.

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 names a specific artifact (a multi-term roadmap starting at start_term) and enumerates what it produces: carried-forward requirements and prerequisites, terms with no published catalog, and graduation-risk notes against the audit's anticipated term. That is concrete and distinguishable from unw_plan_draft, though the opening noun phrase lacks a verb and the parenthetical default clause muddies what exactly is defaulted.

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 explicitly excludes draft-only features (course pins, minimum-load and instructor exclusions) and routes those cases to unw_plan_draft, which is a real when-not rule naming an alternative. It stops short of a positive use statement such as 'use this for a read-only preview before creating a registration plan', so the general selection context is implied rather than stated.

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