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

Annotations only supply the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false); the description goes further by disclosing a real access-control constraint - user-key and OAuth callers can only touch their own rows plus legacy shared rows. It stops short of saying whether marking read is reversible.

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 tight sentences, front-loaded with the action and followed by the scope restriction - no wasted phrasing.

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 no explanation, and the description covers modes plus auth scoping. It leaves a small gap on interactions between 'all' and 'ids' for a mutation tool with no required parameters.

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 only 33% (workspaceId is documented; 'all' and 'ids' are bare), and the description compensates by explaining both modes and their target scope. However, it omits useful constraints such as the 25-id cap and whether 'all' and 'ids' are mutually exclusive.

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 notifications read by ids' or mark all read for the workspace. An agent can distinguish this from the read-side sibling campaignstack_get_notifications, though no sibling is named explicitly.

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 two operational modes (by ids vs. all for the workspace) are implied as branches, but the description never says when to prefer this tool over the read-only get_notifications sibling or any alternative, and lists no exclusions.

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