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

Annotations only indicate openWorldHint=false and destructiveHint=false, which say nothing about side effects beyond that it's not destructive. The description adds valuable behavioral context: clearing the domain via empty string, immediate claimability vs. purchasability depending on payment status, and the action of telling the founder. It clearly explains the timing implications and the webflow, which is more than annotations provide. It does not mention auth requirements, but the timing and exception handling are well covered.

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 description is a bit long but every sentence serves a purpose. It front-loads the primary action and the empty string behavior, then provides contextual timing information. It is well-structured with clear separation between the action and the guidance. The only minor waste is the phrase 'tell the founder' which is agent guidance, but it is useful. Overall, it is appropriately sized for the complexity.

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?

Given the complexity of the domain registration processhare and the existence of an output schema, the description covers the essential operational contexts: when the domain is claimable vs. purchasable, the action to take (telling founder to register), and the clearing behavior. The output schema likely describes the result, so no need to explain return values. It is complete enough for an agent to call this tool correctly in different formation scenarios.

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?

The schema describes formationId as a UUID wrapper, and domain with a pattern and maxLength. The description adds the meaning of 'empty string to clear the selection', which is not in the schema. However, the schema coverage is 50%, so only formationId is described in schema; domain is not described in schema. The description clarifies the domain is the chosen domainclamation but does not provide details on format or validation beyond the schema. It adds the key semantic of clearing but does not fully compensate for the missing domain description. Baseline 3 is appropriate because schema covers 50% and description adds some value.

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 clearly states the action ('Sets the founder's chosen domain on the formation') with a specific verb and resource. It differentiates from siblings like formation_check_domain_availability or formation_create_domain_checkout by clarifying the setting action. The description is immediately clear about what the tool does.

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 provides explicit guidance on when to use this tool: 'for a paid formation the domain is claimable immediately — tell the founder to finish registration now... For unpaid formations the domain is purchasable right after checkout.' It also explains the difference between paid and unpaid formations, which helps an agent decide when to use this tool versus others like formation_create_domain_checkout. It also mentions the empty string to clear, which is a key usage condition.

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