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

Goes well beyond the annotations: it states this writes a real accounting record that cannot be edited or deleted via this server, that the tool never retries, and it discloses concrete rate limits (60/min, 1000/24h). That is unusually rich behavioral context for a creation tool.

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?

Front-loads the action, then dedup guidance, then the return values, then irreversibility and rate limits. Four tightly packed sentences with little waste, though the operational caveats could be trimmed slightly for a first-read skim.

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?

Despite no output schema, the description names the return values (clientId, referenceNumber) and covers mutation permanence, retry policy, and quota—the three things an agent most needs before firing an irreversible 15-parameter create.

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 description contributes no parameter guidance at all, and 5 of 15 parameters lack schema descriptions (67% coverage). The two required fields, name and vat_pc, are documented in the schema, so the schema carries most of the load, but the description adds nothing for the remaining fields such as country, address1/2, or invoice_due_days.

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 ('Add a new client') and even names the underlying API operation (purchasesales/clients:add). It is immediately distinguishable from siblings like smartaccounts_create_sales_invoice or smartaccounts_create_ledger_entry.

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?

Explicitly routes the agent to smartaccounts_list_clients first to avoid duplicate creation, and gives a recovery protocol for ambiguous replies ('look in SmartAccounts before calling again'). This is exactly the when/when-not/alternative guidance the dimension asks for.

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