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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent). The description adds real behavioral context beyond that: flagging pauses the agent's own sending, it routes to a human, and the agent should disclose to its own principal while not confronting the other party. It does not cover reversibility, escalation timing, or auth expectations, so it stops short of a 5.

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?

Purpose and side effect are front-loaded in the first sentence, then conditional use, then post-action behavior. The long lists are not padding — each item is a routing decision — and 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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description covers when to invoke, the pausing side effect, and follow-up conduct. It is slightly silent on what the human review process does next or whether the other party is affected, which keeps it from a 5.

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 50%: reason and messageIds carry inline descriptions while conversationId does not. The description's category-like list loosely maps to the enum values, but it never states how the listed scenarios correspond to a specific parameter. With half the schema documented, this is the baseline 3 — useful framing without compensating for the gap.

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 (flag) plus resource (a conversation) plus the key consequence (human review, pausing own sending). It is clearly distinguishable from adjacent siblings such as block_person, moderate_comment, or read_conversation 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?

Gives an explicit, itemized when-to-use list (threats, sexual content involving a minor, grooming, extortion, scams, self-harm, off-platform pressure, repeated contact after a no) and an explicit when-NOT-to-use list (disagreement, awkwardness, bluntness, one rude message, loneliness, difference). It also tells the agent what to do immediately after flagging. Alternative tools are not named, but the inclusion/exclusion criteria are precise enough to route correctly.

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