Aurion records

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is carried. The description adds scope and currency information the annotations do not: the rooms_* views are explicitly "free rooms, Lille campus today," which tells the agent the data is campus-specific and date-bounded. It stops short of describing result size, empty-result behavior or auth requirements, so it is not fully rich.

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 front-loaded sentence with zero filler; the parenthetical domain groupings do the structural work. It is a dense run of comma-separated tokens rather than a scannable list, which slightly raises parsing cost, but every token is load-bearing.

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?

With one required enum parameter, no nested objects and no output schema, the definition is close to sufficient, and the per-view glosses tell the agent roughly what comes back. It is not complete for a no-output-schema tool: nothing states the shape of returned records (fields, pagination, empty handling), so an agent cannot anticipate the response.

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% and the view parameter carries no per-value documentation, but the description compensates by explaining what each enum value yields (e.g. grades/resit_grades/resit_sessions are results, absences/proofs_of_absence are attendance, rooms_now is Lille free rooms today). That is real meaning beyond the bare enum strings in the schema, though it remains one-word glosses rather than stated output differences.

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 ("Read") and resource ("Aurion record lists") and then enumerates every selectable list, grouped by domain (results, attendance, registrations, free rooms). This lets an agent tell it apart from siblings like aurion_timetable, aurion_certificate and aurion_absence_check without opening any schema.

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?

The imperative "Read one of your Aurion record lists" implies the usage context, but there is no explicit guidance on when to pick this over aurion_timetable, aurion_absence_check or aurion_calendar-style siblings, nor any stated prerequisites or exclusions. The grouping hints at intent but leaves the choice to inference.

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