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

Annotations already declare mutation, idempotency, and non-destructiveness, but the description adds real behavioral detail beyond them: a repeat with the same key returns the task, reports what the original call applied, and changes nothing if the task changed since. Gaps remain around permissions/authorization and whether the assignee is notified, and it never states the normal (non-retry) return value.

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 dense sentences with no filler: the first front-loads the operation and the assignee semantics, the second carries the retry contract. Every clause earns its place and the alternative (unassign) is stated alongside the primary action rather than buried.

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 three-parameter mutation with no output schema, the definition covers the essential contract—assign vs. unassign, id source, and retry behavior. Minor gaps are preconditions (does assignment overwrite an existing assignee? does it require permissions?) and the shape of a successful first-call response.

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 coverage is only 33% (only idempotency_key is documented in-schema), so the description must compensate and largely does: it explains that assigned_to is a member UUID sourced from read('team_members') or whoami, that null unassigns, and that the key must be reused for retries of the same operation. Only task_id is left implicit, which is acceptable given its name and uuid format.

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 ('Assigns a task to a team member') and immediately covers the inverse operation ('or unassigns it with null'), which separates it from siblings like update_task, complete_task, or skip_task. It also tells the agent where the assignee id comes from (read('team_members') or whoami), so the operation is unambiguous without opening the 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?

Gives clear when-to-use context: pass a member id to assign, pass null to unassign, and reuse the same idempotency_key on retries. It does not name competing siblings (e.g., update_task for reassigning via a general edit, or complete_task) or state exclusions such as what happens if the task is already assigned to someone else.

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