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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the safety profile is covered. The description adds one genuinely non-derivable fact: the operation is bulk ("every watch link of a run"), which corrects a natural assumption from the singular name that it targets one link. It adds no detail about whether already-distributed links stop working immediately, or about confirmation/grace behavior beyond the vague "straight away".

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?

One short sentence, front-loaded with the action and the scope, with no filler or redundant clauses. Every word contributes to the meaning.

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 mutation with rich annotations, the definition covers what is affected (all watch links of the run) and that it happens immediately, which is what an agent needs to select and invoke it safely. The remaining gap, the effect on links already shared with viewers and any returned confirmation (no output schema exists), is minor but not fully addressed.

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 a single required runId, and the schema already documents the format (j_…). The description only restates the scoping ("of a run"), adding no new meaning about the identifier or its side effects. Baseline 3 applies when the schema carries the parameter semantics.

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?

"Turn off every watch link of a run" gives a specific verb (turn off/revoke), a specific resource (watch links), and a scope (all links belonging to one run). The agent can distinguish it from create_watch_link without opening the schema. It stops short of naming how it differs from generic link tools such as delete_share_link.

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 implied rather than stated: an agent can infer it should call this when watch links for a run should stop working. There is no explicit when-to-use, when-not-to-use, or mention of an alternative tool for a narrower or different revocation scope.

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