Get notifications

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to restate safety. It adds valuable behavioral context: default time window (7 days), ordering (newest first), hidden system entries unless include_system, and search scope. It does not mention pagination or rate limits, but for a read-only feed with an output schema, this is sufficient. No contradiction with annotations.

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?

The description is a single, dense paragraph that front-loads the core purpose, then adds filtering details, then search. Every sentence adds value, with no filler. It is concise yet comprehensive, and the structure logically flows from what the tool does to how to customize it.

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?

Given an output schema exists (so return structure is documented elsewhere), the description covers the main usage aspects: default time range, type filtering, system inclusion, and search behavior. It lacks explicit pagination or handling of large result sets, and 'student' is ambiguous. However, for a read-only feed with a rich output schema, it is largely complete. The description could mention that results are limited by 'limit' or how to retrieve older items, but it's adequate.

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 must compensate. It explains 'since' (default 7 days ago), 'types' (filter using returned type/type_code values with examples), 'search' (matches text, author or recipient), and 'include_system' (shows hidden EduPage tips/bookkeeping). It does not explain 'limit' or 'student', though 'student' is implied in the context of a student's timeline. This is good coverage, but missing two parameters keeps it from a 5.

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 clearly states it returns 'Everything on the student's EduPage timeline' with a specific verb (get/list), a resource (notifications/feed), and a time scope ('since', newest first). It lists the kinds of items included (messages, homework, grades, etc.), which distinguishes it from sibling tools like get_grades or get_messages that are specialized. This makes the purpose unambiguous.

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 description gives clear guidance on when to use the tool: to retrieve a combined timeline of all notification types. It explains how to filter with 'types' using returned values, how to include system entries with 'include_system', and that 'search' matches text, author, or recipient. It does not explicitly mention alternatives or when not to use it, but the contrast with specialized siblings is implied by calling it 'everything... and more'. This is strong guidance, though a brief mention of 'use specialized tools for single-type queries' would elevate it.

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