canvas_dashboard

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

Annotations already cover read-only, open-world, non-destructive behavior, and the description adds real context beyond them: results carry fetched_at and cache_hit, and there is a short per-account memory cache that refresh=True bypasses. That cache-staleness detail is exactly the kind of trait annotations cannot express; only the precise shape of the "next-step navigation" payload is left unstated.

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 compact sentences with the entry-point cue front-loaded, followed by the navigation model and then the caching note. No sentence is redundant, and the cache note is placed where it matters, next to the only parameter's behavior.

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 annotations, an output schema, and only one optional parameter, the definition covers what an agent needs: entry point, traversal model, freshness metadata, and cache override. Minor gaps remain, such as what qualifies as "active" and whether archived courses are excluded, but nothing blocking is missing.

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 carry the meaning, and it does: refresh=True is explained as bypassing a short, per-account memory cache, which tells the agent both what it does and when a stale read is possible. The cache's "short" duration is not quantified, though the default-false behavior is clear from 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 states a concrete resource and scope: "active Canvas courses with explicit next-step navigation," plus an entry-point role ("Start here"). That distinguishes it from a bare lister, though it never names sibling tools like list_active_courses or canvas_course_home, so the boundary is inferred rather than stated.

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?

"Start here" gives implied orientation guidance for a first call, and the navigation chain suggests it is a stepping stone to deeper tools. However, with many overlapping siblings (list_active_courses, canvas_course_home, canvas_browse_course), no explicit when-to-use/when-not or alternative routing is provided.

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