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

Annotations only declare the write/no-destroy/open-world profile; the description adds real behavioral context: the action 'reaches no one,' 'nothing is sent,' it 'runs without asking,' and the client 'can be deleted' (reversibility). It also states an auth requirement (Cotlet API key with app access). This meaningfully exceeds what the annotations convey.

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 scoping constraint and dedup advice are reasonably front-loaded, but the opening two sentences are largely redundant ('New client in your Clients list' vs 'Creates a client in your Joist account'), and 'Joist' is repeated repeatedly. There is some waste that a tighter phrasing would remove.

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 annotations already covering the safety profile and no output schema to explain, the description covers what an agent needs: what it creates, that it has no external side effects, that it is deletable, that duplicates should be checked, and the auth requirement. Only minor gaps remain.

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 100%, so all four fields (name, email, phone, address) are already documented in the schema. The description adds contextual color (client is 'ready for estimates and invoices') but no field-level syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 gives a specific verb and resource: 'Creates a client in your Joist account,' plus scope context (lands in the Clients list, ready for estimates/invoices). It distinguishes from the sibling list_clients by naming it as a pre-check. It is clear, though the two opening sentences restate the same purpose rather than adding sharper differentiation.

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 explicitly tells the agent to 'Check list_clients first to avoid a duplicate,' naming the alternative and the condition that selects it. It also signals the call is safe to run without confirmation ('runs without asking'). There is no explicit when-not guidance, but the routing to list_clients is concrete.

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