reject_ai_reply

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds genuinely new behavior: the rejection is limited to a single draft, host approval is required, and the reason is persisted on an audit row. It stops short of saying whether the draft is permanently removed or recoverable.

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?

Four short declarative sentences with the scope constraint front-loaded and no filler. The terse fragment style ('Host must approve.') is efficient though slightly ambiguous.

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 mutation with no output schema and zero schema description coverage, the description covers scope, approval, and audit trail but omits confirm semantics, why conversationId is required, and whether the discard is reversible. Adequate but with visible 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?

Schema coverage is 0%, so the description must carry parameter meaning, and it only clarifies 'reason' (stored on audit row) and implicitly draftId/single-draft scope. The required 'confirm' boolean and 'conversationId' get no explanation anywhere.

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 ('one pending AI draft') with explicit scope of exactly one draft. It does not name the natural alternative, approve_ai_reply, so the agent must infer the sibling split from the wording.

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?

'Does not discard other drafts' scopes the action but gives no when-to-use guidance and never mentions approve_ai_reply as the contrasting option for accepting a draft. Usage is only implied by the verb choice.

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