canvas_update_assignment

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

With no annotations supplied, the description carries the full burden and does well: it declares the mutation, the leave-alone semantics for omitted fields, and two non-obvious side effects (publishing unseen assignments, silently re-scaling graded scores when points_possible changes). It does not cover auth requirements or whether edits are reversible.

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-loads the mutation and the downstream-effect warnings before the args list, and every line of the args block earns its place. The repeated 'or empty to leave unchanged' phrasing is slightly redundant but does encode per-field semantics rather than 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 10-parameter mutation tool with no annotations, an output schema (so returns need no explanation) and full parameter documentation, this is nearly complete — side effects, defaults, and formats are all covered. Only authorization/error behavior is absent.

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% across 10 parameters, so the description must compensate fully — and it does. Each parameter is described with meaning beyond its type, including the crucial distinction between empty-string (leave unchanged) for name/description/due_at versus omit for points_possible/published, ISO 8601 UTC date formats, and the CANVAS_DEFAULT_COURSE_ID fallback.

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 ('Edit an existing assignment') and immediately flags the mutation, which cleanly separates it from canvas_get_assignment and canvas_create_assignment in the sibling list. An agent can select it without further inference.

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 explains the partial-update contract ('only the fields you pass are changed; omitted ones are left alone') and calls out two edits with downstream gradebook consequences worth warning an instructor about. It stops short of naming alternatives or stating explicit preconditions such as required permissions.

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