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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false; the description usefully adds that no submission and no charge occur, and that submitted templates are copied rather than modified in place. However, it never explains what the destructive hint means in practice — whether a revised draft replaces prior content wholesale, or what draft_id vs template_id changes about the side effect. With a destructive write tool, that gap is notable but partially offset by the annotation coverage.

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, front-loaded with the two operational modes and ending with a scope-limiting clause; little waste. The middle sentence 'Pass the revised name, body, or examples' is a partial and slightly misleading enumeration given the 13 parameters available.

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?

No output schema exists, so the description would benefit from stating what a successful revision returns (a new draft id?), and the core mechanic — when to supply draft_id versus template_id — is missing for a 13-parameter destructive tool. The absence of charges/submission is a helpful completeness signal, but the parameter-level story is incomplete.

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% across 13 parameters, so the description carries the burden and largely fails. It names only name, body and examples, leaving the required did_id, the draft_id/template_id selector, and fields like language, category, components, buttons, header_text, footer and instructions entirely undocumented 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 two concrete operations: updating an open draft, or copying a submitted template into a new draft. The verb+resource pair ('revise' + 'WhatsApp template') is specific and the dual-mode behavior is disclosed up front. It does not name the sibling tools it differs from (draft_whatsapp_template, submit_whatsapp_template), which keeps it short of a 5.

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?

The description gives clear conditional guidance by mode ('an open draft' vs 'a submitted template') and explicitly bounds scope with 'This does not submit and does not charge,' which steers the agent away from a submit flow. It stops short of naming the alternatives (draft_whatsapp_template for creation, submit_whatsapp_template for submission), so the routing is inferable rather than explicit.

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