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

Beyond the sparse readOnlyHint=false annotation, the description explicitly states that the call WRITES, changes stored state, and is not safe to repeat blindly. This discloses the mutation behavior and repeat-caution clearly. The maintainer-only restriction is an additional behavioral constraint not present in the annotations.

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 two sentences, front-loads the purpose and access restriction, and immediately follows with the critical write warning. No filler or redundancy exists; every sentence earns its place.

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 write tool with no output schema and minimal annotations, the description covers the essential invocation context: who may call it, what it does, and that it mutates state. It does not explain return values or the optional 'secret' parameter, but those are minor given the schema's clear enums and the description's core guidance.

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?

With 0% schema description coverage, the description must compensate, and it does add meaning by stating the reason is 'required public' and listing the three disposition values. However, it does not explain the optional 'secret' parameter or provide any additional semantics for target_type/target_id beyond calling it a 'flagged target'. This is partial but not complete compensation.

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 description clearly states the action ('record') and the resource ('a flagged target'), and enumerates the exact disposition values ('no-action', 'acted', 'watching'). It also differentiates from sibling tools like 'flag' or 'moderate' by specifying the maintainer-only role and the act of recording a disposition rather than creating a flag or moderating.

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 'Maintainer only' prefix gives a clear access context, and the WRITES warning explains that this is a state-changing action not to be repeated blindly. It does not explicitly name alternative tools or when not to use it, but the context is sufficiently clear for a maintainer resolving flagged targets.

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