canvas_unstar

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

With no annotations at all, the description still carries the burden of behavioral disclosure. It does earn credit for flagging mutation ('写操作'), which is the single most important trait for an unannotated tool, but it says nothing about idempotency, what happens if the course is not currently starred, permission/auth requirements, or that omitting confirm triggers a dry run (that detail lives only in the schema).

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?

A single short sentence, front-loaded with the action and its target, with zero filler. It is arguably too terse rather than too verbose, but nothing present is wasted.

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 two-parameter mutation with no annotations and no output schema, the description covers the minimum: what it does and that it writes. It leaves the agent without any account of result semantics (e.g. outcome when the star does not exist) or safety/permission context, which is a meaningful gap for an unannotated write tool.

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 100%, with both course (id or name keyword) and confirm (execute vs preflight) documented inline, so the schema does the heavy lifting. The description adds only the object of the operation and no format, matching, or ambiguity-resolution detail beyond it, making baseline 3 appropriate.

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 ('取消' / un-star) plus a specific resource ('课程个人收藏/星标'), so an agent knows exactly the operation. It does not explicitly name the inverse sibling canvas_star, but the naming symmetry makes the distinction obvious without opening either 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?

Usage is only implied: remove an existing course star. There is no statement of when to prefer this over canvas_star, no prerequisite (e.g. the course must currently be starred), and no note on how the confirm preflight should be sequenced before executing. The '（写操作）' tag is the only usage-relevant cue.

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