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

Annotations already flag destructive/non-idempotent, and the description adds substantial context beyond them: opt_out is permanent, an X send goes out immediately as a DM using Energy, and resending identical text returns alreadyDecided instead of a second message. These are concrete side-effects an agent cannot infer from the schema or hints.

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 the core action, but the remaining content is delivered as long run-on sentences with nested parentheticals (the X-draft clause) that are dense and hard to parse. The information earns its place, yet the structure and readability suffer.

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 complex, 7-parameter, multi-channel mutation tool with no output schema, the definition covers decision semantics, channel differences, prerequisites, and a key return value (alreadyDecided). It omits meaningful handling of 'days' (presumably snooze) and 'decidedBy', leaving small gaps.

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?

With only 43% schema coverage the description must compensate, and it does for the critical params: draftId scope (any channel), leadId restriction (X replies without a draft), and the 'text' precondition of customer-approved wording shown word for word. It leaves 'days' and 'decidedBy' unexplained, so it is strong but not complete.

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 ('Apply one explicit human decision to a pending reply') and enumerates exactly what each decision does (send/invite/booking_link contact the prospect; opt_out is permanent). It is clearly distinct in behavior from the listing siblings, though it never names a sibling to route against, so it earns a 4 rather than a 5.

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 explicit prerequisites ('Show the draft and ask the customer first'), tells the agent which identifier to pass and when ('Pass draftId when it has one... only for an X reply with no draft pass leadId'), and states per-channel constraints ('X accepts only send, snooze, dismiss, opt_out and meeting_booked'). This is textbook when/when-not guidance.

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