canvas_planner

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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered. The description still adds real behavioral context the annotations cannot: results aggregate across all courses, submission states come back labeled (submitted, late, missing, graded, feedback), and dates are interpreted in the caller's Canvas time zone. It does not discuss pagination behavior or ordering, which the page parameter implies but never explains here.

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 purpose, then the recommended use case, then the date conventions. Every clause carries information an agent needs; the parenthetical state list doubles as a return-value preview and is not filler.

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 read-only, four-parameter, no-output-schema tool, the description covers purpose, best-fit scenario, date semantics, and the shape of returned items. The remaining gap is pagination behavior and result ordering, which matter for a potentially large cross-course result set but are left to the schema and guessing.

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%, so the baseline is 3, but the description genuinely adds meaning beyond the field descriptions: it specifies the dates are inclusive on both ends and that a single day is expressed by passing the same date twice. It also ties the interpretation to the Canvas time zone, something the schema's bare 'First day, included.' does not state. It leaves the raw and page parameters entirely to the schema.

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 opens with a specific verb-plus-resource statement: 'Everything due across all your courses in a date range,' then enumerates the item types (assignments, quizzes, graded discussions, to-do notes) and the returned submission state. This clearly separates it from siblings like canvas_assignments, canvas_todo, or canvas_upcoming_events, which each cover only a slice of what this tool aggregates.

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?

It gives an explicit positive trigger: 'The best tool for "what is due today / this week".' That is strong when-to-use guidance. It stops short of naming the alternatives it should be preferred over (canvas_assignments, canvas_todo, canvas_upcoming_events) or stating exclusions, so the agent must infer the boundary itself.

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