list_vilt_registrations

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

Annotations already carry readOnly/idempotent/non-destructive safety, so the description's job is to add context — and it does, substantially. The PII disclosure warning ('EVERY ROW CARRIES A LEARNER'S NAME AND EMAIL... a disclosure this server cannot undo') is a critical behavioral trait no annotation could express. It also clarifies the attended-vs-registered data semantics and the separate API key requirement.

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?

Every sentence earns its place: a crisp one-line purpose, then the critical privacy constraint, the attended/registration distinction, reporting guidance, and the credential caveat. The description is multi-sentence but not bloated — no filler or restatement of the tool name.

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 PII-bearing list operation, this is complete: purpose, param guidance, data sensitivity, semantic field meaning, output reporting expectations, and auth prerequisites are all covered. Output schema exists, so return values need no explanation, and the annotations cover the safety profile. Nothing an agent needs to call this correctly is missing.

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 coverage is 0%, so the description carries the burden. It explicitly names filter_session_id and gives it rich, decision-relevant semantics (scope to one session to avoid exposing PII). Page and page_size are left to convention, but their meaning is self-evident in a list operation, and the warning about 'hundreds of real people's contact details' implicitly signals volume/pagination behavior.

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 sentence 'List who registered for virtual sessions, and whether they attended' names a specific verb, resource, and a distinguishing nuance (attendance vs. registration). This clearly separates it from sibling tools like list_ilt_sessions and list_vilt_session_events without needing to open their schemas.

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?

Explicit when/when-not guidance: 'Ask about ONE session with filter_session_id rather than listing the organization' tells the agent the correct invocation scope and warns against the harmful unfiltered call. It also instructs on response behavior ('Report what was asked... does not need names') and flags the required credential, though it doesn't explicitly name alternative sibling tools.

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