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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false, so the safety profile is covered. The description goes beyond that by disclosing that the record is created as a draft (mutation without immediate publication), the workspace defaulting rule, and the concrete failure mode returned for personal registrations (whatsapp_unverified). It does not address duplicate registrations or what a retry produces, despite idempotentHint=false.

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?

Two sentences, front-loaded with the creation action and its draft state, then the prerequisite and failure path. It is dense with parentheticals, which slightly slows parsing, but there is no filler and every clause conveys operational information.

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 two-parameter mutation with no output schema and a healthy annotation set, the description supplies the essential context: what gets created, in which workspace, the default for the optional parameter, and the one documented error path with its fix. The only material gap is the absence of guidance on validating the business name or handling duplicate drafts.

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 only 50% — `workspace` has an enum but no description — so the description has to carry weight, and it does: it explains the default workspace and the narrow condition under which the parameter should be passed at all. The `name` parameter is already documented in the schema, so the description adds meaning primarily for the undocumented enum parameter.

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 description names a specific verb and resource ('creates the business'), and pins down the exact state it creates ('as a draft') plus its scope ('in the workspace they're in'). That level of specificity separates it cleanly from siblings such as check_name_availability, list_my_businesses, rename_business, or create_share_link without the agent needing to open 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?

It gives concrete conditional guidance for the optional parameter ('pass workspace only when they ask for the other one') and states the prerequisite for a personal registration, naming request_whatsapp_verification as the remedy. What's missing is any routing advice about the adjacent pre-flight tools (check_name_availability, check_business_name_compliance), so the agent must infer whether to validate a name before registering.

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