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

Annotations already declare the safety profile (readOnlyHint false, destructiveHint false, idempotentHint false), and the description adds non-obvious behavior: it auto-generates text in the writer's voice when text is omitted, and it returns the comment plus parent post and linked article. It also explicitly confirms it does not publish, which is the key mutation boundary. It doesn't mention auth needs or whether a draft can be re-created idempotently, so not 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?

Four sentences, action-first, with no filler; the non-publishing constraint is saved for the end as a punctuation point. The long platform enumeration is functional (eligibility) but weighs the first sentence down slightly.

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 not be described, yet the description still names them helpfully. Safety is covered by annotations. The remaining gap is the undocumented substackConnectionId on a tool that spans many platforms, which an agent would need clarified before calling.

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 0%, so the description carries the burden. It usefully explains text's optionality and the auto-generation fallback, and activityId is implied by 'comment ... with canReply true.' However, substackConnectionId is never mentioned, leaving the agent guessing whether it is required for Substack versus non-Substack comments.

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 (save an owned comment reply draft) plus the scope of supported platforms and the eligibility flag (canReply true). The final sentence, 'Does not publish,' cleanly separates it from send_reader_reply_draft and reply_to_reader_activity without needing the 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?

Makes the use case explicit ('for review') and states the precondition that the target comment must have canReply true, which is a real gating rule. The 'does not publish' clause implies the send_reader_reply_draft alternative, but the sibling is never named, so the routing decision is left slightly to inference.

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