List My Planner Items

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

Annotations only declare readOnly/openWorld, but the description adds rich behavioral context: the start_date/end_date must-be-paired rule and Canvas's silent ten-year default window, the ~2-week default echoed back in the response, rejection of an empty context_codes array, the never-null submissions field, and the absent html_url on planner notes. These are real pitfalls an agent could not infer from 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?

Front-loaded with the tool's scope before the enumerated caveats, and every caveat carries actionable content. It is longer than typical, but little is wasted; the numbered structure aids scanning. Slight verbosity in the item enumeration keeps it from a 5.

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 no output schema, the description compensates by explaining return-field behavior (submissions shape, missing html_url, echoed start_date/end_date) and truncation is covered in the schema. For a 5-param, zero-required tool, an agent has everything needed to call it correctly.

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 100% (baseline 3), but the description adds genuine semantics beyond the schema: the pairing constraint on start_date/end_date, the silent default-window failure mode, and the empty-array rejection for context_codes. These inform how to construct values, not just what they mean.

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+resource ('The authenticated student's planner') and enumerates exactly what it returns (assignments, ungraded quizzes, planner notes, wiki pages, calendar events, peer reviews, etc.). It also explicitly distinguishes itself from get_todo_items. An agent can tell this apart from siblings like list_calendar_events or get_upcoming_events without opening a 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?

Explicitly names the closest alternative and the selection rule: 'Strictly richer than get_todo_items, which covers only assignments needing submitting or grading.' This gives clear when-to-use guidance. It does not address other potentially overlapping siblings (list_calendar_events, get_upcoming_events, get_missing_submissions), so it stops short of full exclusion guidance.

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