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

Annotations only declare idempotentHint=true; the description adds that the mark is per-authenticated-user and that it suppresses noise in future queries, which is useful side-effect context beyond the annotations. It does not disclose permission requirements, whether the mark is reversible, or the response shape.

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 tightly written sentences with the action front-loaded and the rationale second. No wasted words, though the second sentence is soft justification rather than operational detail.

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-parameter, idempotent marker with no output schema, the description covers what the tool does and why it exists. The only real gap is the absence of guidance on when to invoke it versus the read-side insight siblings.

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% (the single insight_id is fully documented), so the schema already carries the parameter meaning. The description adds nothing beyond restating which insight is targeted, which is the expected baseline when the schema does the work.

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), a specific resource (insight), and the resulting state (seen) scoped to the authenticated user. It is clearly distinct from sibling readers like get-my-insights-tool, but it never names or differentiates against those siblings 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?

There is no when-to-use guidance, no prerequisite for what a valid insight might be, and no mention of how this relates to get-my-insights-tool. The clause about reducing noise vaguely implies intent but gives the agent no routing condition.

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