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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: results reflect Postproxy's synced cache rather than live Meta state unless refresh is passed, and only APPROVED templates are sendable. It stops short of describing pagination or result-set bounds for a listing 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?

Three dense sentences, front-loaded with the core action and scope, followed by filter dimensions, the refresh switch, and the cross-tool constraint. No sentence is filler and nothing is repeated from the schema verbatim.

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?

With no output schema, the description does carry return-shape burden and partially meets it by naming entry fields (status, variable_count). It is complete enough for correct invocation, though pagination and total-count behavior for a listing endpoint remain unstated.

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 100% and would justify a baseline 3, but the description goes further by enumerating the status values (APPROVED, PENDING, REJECTED, PAUSED, DISABLED) that the schema leaves as a free string with no enum, and by clarifying what refresh actually does beyond the schema's terse 'Sync from Meta before listing'.

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 and resource ('List the message templates on a WhatsApp Business Account') and pins the data source ('as Postproxy has them synced from Meta'). An agent can immediately distinguish this from whatsapp_template_get, whatsapp_template_library_get, and whatsapp_template_create without opening any 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 the filter dimensions (name, language, status) and a clear conditional for the refresh parameter ('Pass refresh: true to pull Meta's current list first'), plus a downstream usage rule tying APPROVED to dm_message_send. It does not, however, say when to prefer this over the sibling whatsapp_template_get or whatsapp_template_library_get, so routing among template tools is only partially resolved.

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