unw_register_preview

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

With no annotations, the description carries the full burden and does well: it declares the tool is non-mutating, discloses the two-stage execution (remote Banner eligibility call, then local CRN checks), and warns that prereq_ok is null when unverified. It omits cost/latency expectations for the remote Banner call and says nothing about what the refresh flag changes, which are meaningful for a networked read.

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?

Three sentences, front-loaded with the most decision-critical constraint (DRY RUN ONLY) before the mechanics. Mild redundancy between 'never posts add/drop/register' and 'never attempt real registration', but both reinforce a safety-critical boundary rather than pad the text.

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?

No output schema and no annotations, but the description enumerates the return content (eligibility flags, failure text, seat availability, time conflicts, prerequisite status) well enough for an agent to consume results. The unexplained refresh parameter is the one real completeness hole for a 3-parameter tool.

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 define the parameters, and it only partly does: it explains that term drives Banner eligibility and that CRNs drive the local seat/conflict/prereq checks, but never explains the refresh flag or the accepted CRN formats (array, string, or integer) in the schema. Roughly two of three parameters gain meaning.

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-plus-resource outcome (returns Banner term eligibility flags and local CRN checks) and front-loads the scope qualifier 'DRY RUN ONLY: never posts add/drop/register'. An agent can immediately tell this apart from the plan-mutation siblings such as unw_banner_plan_add.

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?

Gives clear when-to-use context (pre-flight verification of term eligibility and CRN conflicts) and an explicit when-not clause: 'never attempt real registration'. It also tells the agent how to short-circuit on an ineligible term. The only gap is that it never names the sibling tool that performs the actual registration, so the agent must infer the hand-off target.

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