Add watcher

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

Even though annotations already provide idempotentHint=true, destructiveHint=false, and readOnlyHint=false, the description adds genuinely useful behavioral context: the notification side effect, idempotency in plain language ('adding an account that already watches changes nothing'), and the permission boundary. It also explicitly frames the operation as reversible and as 'a standard write rather than a destructive one', reinforcing the destructiveHint annotation rather than merely repeating it. No statement contradicts the annotations.

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 of roughly 70 words, each carrying distinct information: purpose and effect, idempotency plus permissions, then reversibility and the rationale tying back to the non-destructive hint. The core behavior is front-loaded before the caveats, and there is no repetition of schema content. Nothing could be removed without losing signal.

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 moderate-complexity write tool, the description plus schema is complete: the description covers permissions, idempotency, reversibility, and notification semantics, while the schema covers the plan/apply mode, profile locking, and accountId format. The absence of an output schema is immaterial for a write that returns no meaningful payload. The only minor omission, pointing to jira_list_watchers for verification, is not required for correct invocation.

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%, and the input schema already carries rich descriptions for all five parameters, including the accountId-vs-username pitfall and the plan_id/apply handshake. The description itself adds no parameter-level detail, so the 100%-coverage baseline of 3 is appropriate. This is a correct division of labor rather than a gap.

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?

Opens with a specific verb and resource plus an observable effect: 'Makes an account watch an issue, so Jira notifies it of every change.' The wording makes the direction of the operation unambiguous and separates it from read siblings like jira_list_watchers and from the reversal sibling jira_remove_watcher. The behavioral consequence ('notifies it of every change') clarifies what 'watch' actually means.

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 description gives clear permission conditions: adding someone else requires the 'Manage watchers' permission while adding yourself does not, so an agent can predict success or failure. It also names jira_remove_watcher as the reversal path and states that re-adding an existing watcher is a no-op, guiding when the call is unnecessary. It does not explicitly contrast with the analogous jira_add_vote or suggest jira_list_watchers for pre-checking, which keeps this at a 4 rather than a 5.

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