Course snapshot

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description's one real addition is "no Canvas calls" — implying local cached reads — but it never says how stale the snapshot can be or how it relates to canvas_run_snapshot refreshing it, which is the key behavioral caveat for a cache-read tool.

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?

Two sentences, zero filler, with the most decision-relevant fact ("no Canvas calls") and the compactness trade-off front-loaded. Every clause carries information the agent can act on.

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 3-parameter read tool with annotations present and no output schema, the description is serviceable but thin: it never characterizes the return shape beyond "compact", doesn't explain how text_chars truncation manifests, and doesn't mention staleness or how a snapshot is refreshed. An agent can call it, but not fully predict what it receives.

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 only 33% (text_chars alone is documented), so the description does real work: it enumerates the kinds vocabulary and gives a concrete example ("["assignment"] for all deadlines and grades") that explains intent, not just the allowed strings. It does not clarify course_id's expected format, which is the main remaining gap.

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 resource and scope: the stored/cached state of one course from the latest snapshot, explicitly "(no Canvas calls)". This differentiates it from live-fetch siblings like canvas_list_assignments, though it never names those siblings directly, so the differentiation must be inferred from the parenthetical.

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 only guidance is about parameter usage ("Use kinds ... to keep it small"), not about when to choose this over canvas_list_assignments or canvas_run_snapshot. Nothing tells the agent when the cached snapshot is preferable (speed?) versus when freshness requires a live call.

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