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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds substantial context beyond them: the partial-success model (updated/skipped/errors), the meaning of each bucket, per-task error codes (NOT_FOUND / PROJECT_ACCESS_DENIED), and the 200-task cap. This is exactly the write-behavior disclosure an agent needs.

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?

Front-loaded with the purpose sentence, then parameters/alternatives, return shape, limits, and permissions in a logical order. Every sentence carries distinct information (mutual exclusivity, return buckets, error codes, cap, permissions) with no padding.

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?

With no output schema, the description discharges the return-value burden by describing the { updated, skipped, errors } shape and error codes, and it covers limits and auth requirements for a mutation tool. Nothing an agent needs to invoke it correctly is missing.

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 mutual exclusivity of assigneeId/assigneeEmail, the null-to-unassign semantics, and email resolution are already documented in the schema. The description largely restates these, so the baseline 3 for a fully-covered schema applies.

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+resource+scope: '(un)assign multiple tasks to one person in a single call.' It also distinguishes itself from the sibling assign_task by naming the exact differentiating capability (optimistic concurrency via expectedAssigneeRevision), so an agent can tell the two apart without opening either schema.

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?

Names the alternative explicitly ('Use the single-task assign_task when you need optimistic-concurrency') with the condition that selects it, and states the caller prerequisite (task.assign on each project) plus the target constraint (active org member). Nothing about routing or eligibility is left to inference.

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