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

Annotations already declare destructiveHint=true and idempotentHint=true; the description adds the genuinely useful scope limit — the site, project and list records survive untouched, only the association is severed. That materially reframes a 'destructive' tool as a low-blast-radius one. The "Write tier" label is unexplained internal jargon.

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 short clauses, front-loaded with the action and the exclusive-or constraint, then the non-effect. Every sentence carries information; nothing is padding.

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 write with rich annotations and no output schema, the agent knows what is removed, what is preserved, and that it is idempotent. Only failure behavior for a nonexistent link or mismatched ids is unaddressed.

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 carries the burden and partially meets it: it explains what project_id and list_id mean and that they are mutually exclusive. It says nothing about site_id beyond the name, nor about formats or how to discover valid ids.

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?

A specific verb-resource pair: it removes a site's link to either a project or a task list, and states that the link is the only thing removed. The unlink-vs-link distinction against tascan_link_site is inferable from the wording, though the sibling is never named.

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?

"exactly one" of project_id or list_id is a hard invocation constraint that prevents a common misuse, but nothing says when to prefer this over alternatives such as tascan_update_site or when a link must exist first. Usage is implied by the parameter rule rather than explained.

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