manage_queue_watchers

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

Despite destructiveHint=true already being annotated, the description adds rich behavioral disclosure beyond it: full replacement of existing members, silent skip-and-report behavior for unresolvable members while the call still succeeds, and the constraint that system groups and role groups do not resolve. The explicit warning to 'confirm every member you passed was actually added' surfaces a genuine partial-failure trap that annotations alone would not reveal.

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?

The core operation is front-loaded in the first sentence, and every subsequent sentence addresses a distinct failure mode or constraint (bare-name lookup failure, system/role group exclusion, single-value role exclusion, partial update reporting). It is dense but economical; a minor structural refinement would be breaking the qualification rules into a list, but nothing here is wasted.

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 destructive tool with 4 parameters, a nested CustomRoles object, and no output schema, the description covers the inputs thoroughly, including member formats and role constraints, and even hints at return behavior via 'returned messages.' The only gap is the dangling 'see PARTIAL UPDATES' reference — that section is not present in the description — and the exact output format is never specified in the absence of an output schema.

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%, so the baseline is 3. The description earns a point above baseline by adding semantic details the schema lacks: the group: prefix convention, the replace-not-append semantics of the lists, and the eligibility restriction on single-value custom roles. It does not restate the schema's per-parameter 'username, email, or ID' text, which is correctly left to the schema.

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?

The description opens with a specific verb+resource: 'Set the members of a queue role (Cc, AdminCc, or a multi-value custom role).' It goes beyond a bare statement by clarifying the scope (which roles are affected) and the set-replacement semantics, which distinguishes it from adjacent tools like update_queue (settings) and the group membership tools in the sibling list.

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 provides substantial operational context: members are passed as a complete list that replaces existing ones, groups require a 'group:' prefix, and only multi-value custom roles are eligible. It does not explicitly route to or away from sibling alternatives, but there is no close competing sibling for this operation, so the exclusion guidance is not strictly needed.

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