Mark Notifications Read

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

Adds real context beyond annotations: the mutation is limited to the read flag ('Only changes the read flag'), and it discloses an authentication requirement ('Requires a wallet signature identity'). The idempotency claim merely restates idempotentHint, and the openWorldHint implication isn't discussed, but overall this exceeds the annotation baseline.

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 with the mutation scope front-loaded and the auth note trailing; 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?

For a one-optional-parameter mutation with an output schema and solid annotations, the description covers scope, mutation blast radius, and auth. Edge cases like no-op results or permission failures are left to the output schema and annotations.

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% and the schema already states 'omit to mark everything read', so the description's handling of `id` adds little beyond it. Baseline 3 applies since the schema carries the parameter semantics.

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 ... as read') and resource (notifications), and distinguishes the two modes: single notification by `id` versus all when omitted. It doesn't explicitly contrast with `tronsave_list_notifications`, but the write verb makes the boundary obvious.

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?

Clearly explains the condition that selects the broadcast behavior ('when `id` is omitted, ALL of the user's notifications'), which is the main invocation decision. It gives no exclusions or pointer to the sibling listing tool for retrieving notifications first.

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