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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the description's main added value is the outcome framing ('never sent'), which clarifies the intent of the deletion. It does not say whether this is reversible, what state the draft/lead ends up in, or whether a notification is emitted — all relevant for a destructive, non-idempotent call.

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?

A single short sentence with no filler and the outcome up front, but it is terse to the point of under-specification for a destructive operation. Nothing is wasted, yet the brevity costs clarity rather than buying it.

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, non-idempotent mutation with an undocumented required identifier and no output schema, the description should cover irreversibility, which object is affected, and how to obtain the messageId. None of that is present.

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%: messageId carries only a uuid format and pattern, with no explanation of what message is being referenced or where to obtain it. The description never mentions the parameter, so it compensates for none of that gap.

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?

The sentence 'Remove a draft so it is never sent' gives a verb and an outcome, but the tool name says 'leads_reject' while the description talks about deleting a draft — the agent has to reconcile 'reject a lead' with 'remove a draft' on its own. No sibling is named, and the many nearby draft-removal tools (soclo_autopilot_reject_draft, soclo_leads_archive, soclo_posts_cancel) are left undistinguished.

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?

There is no statement of when to call this versus soclo_leads_edit, soclo_leads_archive, or soclo_autopilot_reject_draft, and no preconditions such as the draft still being pending. Usage is only inferable from the title.

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