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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=true), so the description's main added value is the post-condition that 'the link stops working'. That is useful but borders on restating 'unshare', and nothing is said about what happens to existing consumers of the link or whether the run itself is affected.

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 front-loaded clause with zero filler; the scope constraint and the observable effect are both packed into one sentence.

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 simple ownership-scoped toggle with one fully documented parameter, an output schema, and annotations covering safety and idempotency, the definition supplies enough to call correctly. Minor gap: no note on whether the run's data or existing shared access is otherwise affected.

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% and the run_id parameter already documents its origin (list_runs or save_run). The description only echoes the ownership constraint ('caller's runs'), which the schema already conveys, so it adds essentially no new parameter meaning.

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 and resource ('Turn off the public link of one of the caller's runs'), which is clearly distinct from sibling tools like share_run, delete_run, and close_paper_run. It stops short of naming the inverse operation (share_run) explicitly, but the pairing is unambiguous.

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 ownership qualifier ('one of the caller's runs') implies the precondition, but there is no explicit when-to-use guidance and no exclusion versus delete_run or close_paper_run, which a caller might confuse with link removal. Usage is inferable rather than stated.

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