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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavior ('Returns 404 if the task is not in the active workspace'), which tells the agent how failure manifests. It doesn't mention ordering or pagination, but for a filtered read that is a minor gap.

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?

Two short sentences with zero waste. The core operation is front-loaded and the 404 behavior follows as supporting detail.

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, fully annotated, single-param read tool this is nearly complete: it names the returned entity (the users assigned) and the failure mode. With no output schema, a brief note on ordering or empty-result behavior would be the only addition, which is a small gap rather than a blocking one.

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?

There is a single parameter (taskId) with 100% schema coverage, so the schema already documents it. The description's phrase 'one task' reinforces that exactly one task id is passed, but adds no format or syntax detail beyond the schema. Baseline 3 is appropriate.

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 ('List the users assigned to one task') and adds the scoping qualifier 'server-side filtered', which separates it from the broader list_assignments and from get_assignment. It stops short of naming those siblings explicitly, so differentiation is implied by scope rather than spelled out.

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: call this when you have one task id and want its assignees rather than all assignments. The 404 note hints at a precondition (task must be in the active workspace), but there is no explicit when-to-use/when-not guidance or named alternative.

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