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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds the critical detail that 'bin' means deletion after 30 days, which annotations do not convey, giving an agent real consequence information before calling.

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 description is short, but it is a dense semicolon chain that is hard to parse. The first sentence is front-loaded with the core action, but the second sentence crams several conditional behaviors into one run-on clause.

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 and annotations cover return values and safety, and the description supplies the 30-day deletion note. It still leaves ambiguity about parameter combinations, such as whether item_ids are required for all mark values and how plugin_id relates, so an agent may hesitate on edge cases.

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 80%, so the schema already documents most parameters. The description adds combinational semantics such as 'with mark read, also account notice ids' and 'all: every notice, or every new form reply', but these are terse and partially redundant with the enum 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?

The first clause states a specific verb and resource ('Marks form replies or bookings'), but the scope quickly expands to notices, orders, and account notice ids, making the actual domain muddled. An agent can infer it is a bulk-marking tool, but the jargon ('mark', 'bin', 'nt_…') obscures the precise purpose.

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 phrase 'only when the user asks' gives one explicit guardrail, and the description implies use with specific mark values. However, it names no alternatives and does not state when not to use this versus other mutation tools.

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