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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: it is a local-only discard ('No TikTok changes') that preserves completed item receipts, which the annotations cannot express. It does not cover idempotency or error behavior.

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?

Two short sentences, zero filler. The scope and state precondition are front-loaded, and the effect disclaimer follows immediately.

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 destructive lifecycle tool with no output schema, the description covers the important unknowns: which states are deniable, what survives (completed receipts), and that no external system is touched. It stops short of saying what the caller receives back or what happens to incomplete items.

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% across 3 parameters, so the description carries the full burden and documents none of them. approval_ref, expected_plan_digest, and the connection_context pattern are left entirely unexplained, including the digest's role as a concurrency/confirmation guard.

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 (discard) and resource (a prepared or quota-waiting mixed approval), and qualifies which lifecycle states are eligible. 'No TikTok changes' implicitly separates it from approval_plan_confirm, which is the sibling that does touch TikTok. The jargon 'mixed approval' is left undefined, keeping it from 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?

The phrase 'prepared or quota-waiting' gives a concrete precondition for when this tool applies, and 'No TikTok changes' contrasts with the confirm path without naming it. There is no explicit 'use X instead when...' routing, but the context is clear enough to select correctly.

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