draft_followup

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real substance beyond them: it will not send or mutate contact history, and it defines the output contract that a host may reword the text but must preserve uncertainties and source references. That is a genuine behavioral constraint an agent needs to respect.

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 with no filler, and the core purpose plus the negative constraint are front-loaded. The split into two paragraphs is slightly awkward for such a brief definition but nothing is wasted.

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 described, and the behavioral constraints are covered. The remaining gap is the required integration_id, undocumented in both schema and description, which leaves the caller guessing what evidence source to bind.

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%, so the description must carry parameter meaning. 'Bilingual' loosely signals that a language choice exists (matching the lang enum), but the required 'integration_id' is never explained and no format, source, or selection guidance for lang is given.

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 ('Prepare') and resource ('evidence-bound bilingual template'), so the agent knows it produces a draft artifact rather than sending anything. However it never names 'follow-up' explicitly nor distinguishes itself from the sibling draft_ticket, so an agent cannot tell the two drafts apart from the text alone.

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 send or update contact history' implicitly scopes usage to a preparation-only step, and the name suggests drafting a follow-up. But it never says when to prefer this over draft_ticket, validate_draft, or triage_issue, nor any prerequisite or ordering guidance.

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