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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent). The description adds genuinely useful audience context ('the customer never sees it'), but it says nothing about the idempotency behavior that the schema only hints at via requestId, nor about permissions or notification side effects beyond mentions.

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?

Three short sentences, front-loaded with the core action and scope. The visibility sentence earns its place; the mentions sentence is slightly redundant against the schema but still brief and on-point.

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 simple, well-documented four-parameter mutation with clear annotations and no output schema, the description covers what and audience. It is close to complete; only the when-to-use routing against reply_to_conversation and save_reply_draft is missing.

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 100%, so the schema already documents all four parameters, including the requestId repeat-safety semantics. The description's mention guidance ('Mention teammates by user id to notify them') largely restates the existing mentions parameter description, adding no new syntax or format detail.

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 and resource ('Add an internal note to a conversation') and distinguishes itself from the reply-family siblings by making clear the customer never sees it. It never names a sibling like reply_to_conversation or save_reply_draft explicitly, so the differentiation is implicit rather than stated.

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?

Usage is only implied: an agent can infer 'use this when you want an internal-only annotation rather than a customer-facing reply.' There is no when-to-use statement, no exclusions, and no named alternative among the many conversation-related siblings.

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