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

Annotations already flag destructiveHint/openWorld/non-idempotent, but the description adds genuinely new context: messages cannot be recalled, non-followers receive it as a message request, and each call requires owner approval. The approval/confirmation note is slightly redundant but the request/irreversibility details are valuable.

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?

Front-loaded with purpose and targeting, then behavior. Mostly every sentence earns its place, though 'By default you confirm each call; you can switch that off' and 'Waits for the owner's approval' overlap in content.

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 3-param mutation tool with full annotation and schema coverage and no output schema, the description covers targeting, side effects, and approval flow adequately. Only the return/response shape (e.g., resulting conversation id) is unaddressed, which is minor.

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% (baseline 3), and the description adds meaning beyond it: it clarifies the exactly-one-of constraint between conversation_id and user, and that a user-targeted message may start a new conversation. That constraint is not expressed in the schema.

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 ('Send a direct message on Substack') and immediately disambiguates the two targeting modes (conversation vs. person). An agent can distinguish this from reply_to_comment or publish_note from the description alone.

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?

Explicitly says 'Give one of conversation_id or user,' which is a clear selection rule, and explains that with conversation_id it replies there while user targets a person. It lacks an explicit statement of when to prefer a sibling like reply_to_comment, but the targeting guidance is strong.

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