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

Adds genuinely non-obvious behavior beyond the annotations: forwarded senders are learned by default with an opt-out ('learn': false), and the operation is reversible by re-assigning. It also discloses the confirmation model (runs immediately, no plan_token, only the caller's own record). Minor tension: annotations flag destructiveHint=true while the description frames it as trivially undoable and immediate, but it never claims the call is read-only, so this is framing rather than contradiction.

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 core action and input shape, then the side effect, then the confirmation policy in a labeled block. Dense but nearly every clause carries information; the CONFIRMATION paragraph is longer than strictly needed for this tool since most of it describes tools other than this one.

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 7-parameter destructive mutation with no output schema, the description covers the operation, its side effects, reversibility, and the confirmation contract. It stops short of stating precedence or conflict behavior when capture_ids and session are both supplied, or what happens if 'label' names a nonexistent label without create_if_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?

With only 14% schema description coverage, the description carries the load and does so: it defines 'label' as id or name/alias, explains 'create_if_missing' makes a new label from the name, clarifies 'own' and 'clear' as alternatives, and explains what 'learn' toggles. Only 'capture_ids'/'session' mutual exclusivity and the 500-item cap are 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?

States a specific verb and resource ('Put captures under a client label, or mark them the caller's own') and enumerates the three mutually distinct outcomes (label, own, clear). An agent can tell this is a labeling/marking operation on intake captures rather than a query or a label-management call.

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?

Specifies the input shape to use ('Pass capture_ids or a session id, and one of: label, own: true, or clear: true') and gives an undo path ('Undo by assigning again'). It does not explicitly route the agent away from the sibling label-management tools (intake_manage_labels, intake_list_labels), though 'create_if_missing' implicitly covers the create-a-label-while-assigning case.

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