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

Annotations already declare destructiveHint=false, readOnlyHint=false, and idempotentHint=true, so the safety profile is largely covered. The description adds genuinely useful context by clarifying that a rejection publishes nothing and deletes nothing, which tells the agent the draft survives the call. It stops there – no mention of what is returned or whether a rejection can be reversed by a later approval.

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, each doing distinct work: what is recorded, when to call it, and what side effects do not occur. The scope statement is front-loaded and nothing is redundant.

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 two-parameter mutation with annotations covering safety and idempotency and no output schema, this covers the essentials: the action, the precondition, and the non-destructive outcome. The remaining gap is what id actually references and what happens to the draft afterward, which would matter to an agent reasoning about follow-up calls.

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 50%: person_asked is fully documented in the schema, but id has no description at all in either place. The phrase 'one waiting draft' implies id identifies a draft, which is mild added meaning. For a required parameter with zero schema documentation, the description could have done more (e.g., that id is the draft identifier, not an item or person id).

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: 'Record the owner's no to one waiting draft.' An agent can tell this is a rejection decision on a pending draft. It stops short of naming the obvious counterpart, approve_item, so the distinction from that sibling is left implicit.

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 a clear positive condition ('Only call this when the person asked for this item to be turned down') and a strong exclusion against acting on the agent's own judgement, reinforced by the person_asked parameter. It never references approve_item as the alternative path, so sibling routing relies on inference.

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