mark_principal_notifications_read

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

Goes well beyond annotations: per-id refusal of notifications not returned by the sibling read tool, the required principal token with write access, and the read-only-token failure mode with the message to relay to the user. Annotations cover the safety profile (idempotent, non-destructive), and the description adds prerequisite and partial-failure semantics.

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-loads the core action and the disambiguation before anything else, and every sentence carries new information. Slightly dense as a single paragraph with several parentheticals, but nothing is wasted.

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 an output schema present the return shape need not be described, and the description still covers scope, selection modes, prerequisite auth, and partial-refusal behavior. Nothing an agent needs to call this 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 coverage is 100%, so the baseline is 3; the description adds meaning by framing only_agent_actors as 'fleet bookkeeping' and clarifying the interaction between before and only_agent_actors (only unread agent-caused notifications created before a date).

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 (mark read) and resource (notifications in the principal's inbox), and explicitly positions itself as the write twin of get_principal_notifications and as distinct from the similarly named mark_notifications_read. An agent can disambiguate among siblings without opening any 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 two selection modes explicitly (pass ids, or only_agent_actors: true for agent/integration-caused unread notifications) and the alternative tools it must not be confused with. It also states the constraint that only notifications previously returned by get_principal_notifications are markable.

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