Mark an insight read

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

The annotations only supply the safety profile (readOnlyHint=false, destructiveHint=true, idempotentHint=false), and the description adds genuinely non-structured context: the underlying endpoint, required OAuth scope (luca:draft), required scope (insights:write), that an Idempotency-Key is required and will be server-generated if omitted, and the redacted data sensitivity. It does not explain what state change 'read' actually persists, but the added operational detail is substantial.

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 purpose is front-loaded in the first sentence, followed by compact metadata lines (endpoint, scopes, idempotency, workspace override). Each line carries distinct operational information, though the block of scope/metadata lines reads more like a spec dump than a narrative and could be trimmed slightly.

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?

An output schema exists, so return values need not be described. Combined with annotations covering the safety profile, the description supplies auth/scopes, idempotency behavior and workspace fallback, making it sufficient to invoke the tool correctly; only the precise post-condition (does read affect the feed, the unread count, or both) is left unstated.

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 75%, with id, workspaceId, workspaceSlug and idempotencyKey all documented in the schema. The description still adds value by clarifying that the idempotency key is effectively required for retry safety and that workspaceId/workspaceSlug override the environment-configured default workspace, giving semantic weight beyond the terse schema descriptions.

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 ('Mark one insight read') and adds the observable effect ('stops coming back at the top of the feed'), which separates it from sibling insights tools like luca_insights_dismiss or luca_insights_mark_actioned to some degree. It stops short of explicitly naming those siblings, so the differentiation is inferential rather than stated.

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 effect statement ('so it stops coming back at the top of the feed') implies when an agent would want this, but there is no explicit when-not guidance and no reference to the alternative insights actions (dismiss, mark_actioned). Usage is left to inference from the sibling namespace.

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