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

Annotations only declare destructiveHint=true; the description goes far beyond by disclosing the exact state change (message set to handed_off), the full blast radius ('closes the person out everywhere', contact reads closed on every surface), the sole reopening condition (a new inbound message, with the hourly inbox sweep), and that acceptance can no longer revive them. This is exactly the behavioral context an agent needs before an irreversible action.

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?

The core meaning is front-loaded in sentence one and the critical warning is bolded. The hold-versus-stop distinction is restated twice (once as 'NOT A HOLD', once as the quoted 'keep the sequence alive' case), which is mild redundancy, and the third paragraph is a long compounded sentence — defensible given the stakes, but not maximally tight.

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, high-consequence tool with no output schema and no required parameters, the description covers what changes, what persists, who can be affected across campaigns, and how to reverse it. Nothing needed to invoke it safely is missing.

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 100%, so the schema already documents contactId, campaignId, profileUrl, profileUrls, messageId, and reason with rich per-field guidance. The description adds no parameter-level syntax or format detail, so the baseline 3 applies.

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?

Names a specific verb and resource ('Stop a contact entirely') and immediately scopes the meaning with '(not a fit / do-not-contact)'. It explicitly distinguishes itself from li_mark_outcome, li_cancel_steps, and li_reset_contact, so an agent can route correctly without opening any sibling schema.

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 explicit when-to-use ('Only reach for this tool when you mean the person is finished with'), names the exact wrong-intent alternative for the common confusion ('do not send this message, but keep the sequence alive' -> li_cancel_steps), routes outcome-recording elsewhere, and discloses the undo path via li_reset_contact with its precondition.

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