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

Annotations already declare destructiveHint=true/readOnlyHint=false, so the safety profile is covered; the description adds the non-obvious scope fact that the discard is local only ('No Meta write'), which materially changes the agent's risk assessment. It does not say whether the token is single-use or what state the draft ends in, so it stops short of 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?

Two dense sentences: the action and its key first, the Meta-write exclusion second, the fallback path third. No filler, no repetition of the title, everything 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 need not be explained, and the description covers action, scope, and failure recovery. Minor gaps remain: whether the token is consumed on use, and what the caller should do after a successful deny (e.g. re-prepare). Adequate for a 2-parameter tool.

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% for 2 parameters, so the description must compensate. It clarifies that confirm_token must be the 'exact' token for the draft, which is useful, but connection_context is completely unaddressed and no token format/provenance is given beyond the lost-token recovery note.

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) applied to a specific resource class (prepared QuickCreate / recreate / ad-copy / structural-clone draft) and names the exact key required (confirm_token). It is clearly distinguishable from launch_confirm and from operations_deny_approval, which it explicitly routes to.

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 the normal path, the crucial exclusion ('No Meta write'), and a concrete alternative workflow for the failure case ('For a lost token, use operations_get_approval then operations_deny_approval with approval_ref and expected_plan_digest'). Nothing about when to pick this over a sibling is left to inference.

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