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

Goes beyond the annotations by disclosing that the new client is visible instance-wide, that a duplicate tax id is rejected, and what the minimum required payload is. These are real operational constraints not available from readOnlyHint/idempotentHint/destructiveHint. It still doesn't mention what is returned (e.g., the new client id) or any auth/rate-limit expectations.

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?

Four tight sentences, front-loaded with the WRITE marker and endpoint. Every sentence carries a constraint; nothing is filler.

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 non-idempotent write with 13 mostly optional params and no output schema, the description supplies the key behavioral facts (visibility, dedup, minimum payload). Only the return value and the idempotency implication of retries are unaddressed.

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 only 38% across 13 parameters, so the description should compensate more. It adds the first_name-or-company requirement and ties 'code' to tax-id uniqueness, but leaves email format, phone, address, note, and is_foreigner behavior to the schema.

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 ('create a new customer in Bsale') plus the underlying endpoint POST /v1/clients.json. An agent can immediately distinguish this from bsale_update_client, bsale_get_client, and bsale_list_clients.

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 'Give at least a first name or a company' rule tells the agent the minimum viable call, and the tax-id uniqueness note warns about failures. However, it never says when to prefer bsale_update_client over creating, or to check bsale_list_clients/bsale_get_client first for duplicates.

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