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

Far exceeds the annotations: it discloses that only one contact is created, that no message is sent to the client, that no confirmation prompt occurs, that the client record governs currency/tax/language/terms for future invoices, the Free-plan cap of 5 clients, and the API-key requirement. Annotations only cover read-only/destructive/open-world, so this is substantive additional context.

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-loaded and mostly earned, but the one-contact-created point is stated twice ('Add a client with one contact' then 'Creates a client with one contact'), and the Cotlet API key line is bolted on at the end. Tightening would remove obvious redundancy.

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 6-parameter create tool with no output schema, the description covers the return value (client ID), the mutation's downstream consequences, plan limits, and auth needs. Nothing an agent needs to call it correctly is missing.

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 100%, so the baseline is 3, but the description adds real meaning by explaining the downstream effect of the currency field and the fact that the contact fields are a single embedded contact. It still doesn't clarify why company/contact_last_name are optional or how company selection interacts with defaults.

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/Creates a client with one contact') and adds distinguishing details: it returns the client ID and the record carries billing defaults. An agent can separate this from list_clients or create_invoice without opening the 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?

Gives a concrete usage rule ('set the currency here if it differs from your company default') and sets expectations about approval ('runs without asking first'). It stops short of naming when to prefer a different sibling tool or when a client already exists.

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