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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false. The description adds that it records the revision and does not publish – useful context beyond annotations. However, it doesn't mention permission requirements, rate limits, or what happens on a missing/expired expectedUpdatedAt.

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, no waste. The purpose comes first, then the concurrency-token instruction, then a scope boundary. Well front-loaded.

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 don't need explanation. But for a 4-parameter mutation tool with 0% schema coverage, the description omits critical parameter semantics (what 'text' represents, whether substackConnectionId is required). It covers the concurrency token but leaves gaps for an agent to fill.

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%, and the description only explains expectedUpdatedAt (its purpose as a concurrency token). The other three parameters – text, draftId, substackConnectionId – have no semantic guidance in the description. With zero schema coverage, the description should do more to compensate.

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 states a clear verb+resource: 'Edit an unsent reply draft and record the revision.' It distinguishes itself from send_reader_reply_draft by noting 'Does not publish.' It could be clearer about how it differs from update_draft or create_reader_reply_draft, but the core purpose is unambiguous.

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 phrase 'Edit an unsent reply draft' implies usage – you use it on drafts that haven't been sent. But there's no explicit when-to-use vs alternatives guidance, and no mention of what happens if the draft was already sent. The 'Does not publish' note provides a soft boundary against send_reader_reply_draft.

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