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

With annotations supplied, the bar is lower, and this description still adds real behavioral context: the URL serves 410 afterwards, and republishing restores the same URL, which explains why destructiveHint=false and idempotentHint=false. It does not cover permission requirements or the result of a second unpublish call on an already-removed page.

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 action, then consequences, then the parameter source. No filler and nothing repeated from the schema or annotations.

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 one-parameter, no-output-schema, reversible toggle, the description covers action, side effect, reversibility and id provenance — enough to call it correctly. Minor gaps remain around repeated invocation on an already-unpublished page and any authorization requirement.

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% with a documented publication_id, so the baseline is 3; the description earns an extra point by naming an alternate source for the id (the organisation's published pages list) that the schema does not mention.

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?

Specific verb + resource: "Take a published canvas page down." It names the exact artifact (a published canvas page) and is unmistakably the inverse of the sibling publish_canvas, so an agent can separate the two without reading 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?

It gives clear invocation context by stating the two legitimate sources of the required id (publish_canvas's return value, or the organisation's published pages list) and implies when to use it (to remove a live published page). It stops short of stating exclusions, e.g. what to do if the page is already unpublished.

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