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

Annotations already declare readOnlyHint=false and openWorldHint=true. The description adds context beyond them: the message appears in the same thread as the provider panel, a per-call confirmation is the default, and a Cotlet API key with app access is required. Useful, though it doesn't describe delivery failure modes or rate limits.

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 first two sentences say essentially the same thing twice ('Write to a customer... or to the Civitatis booking department' then 'Sends a message about one booking, to the customer or to the Civitatis booking department'), which is wasted space. The auth and confirmation details do earn their place, but the lede is repetitive.

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 3-parameter messaging tool with no output schema, the definition covers the essentials: target audience, thread behavior, confirmation policy, and auth requirement. The only gap is that no sibling reader tool is referenced to check existing threads.

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 schema already documents to/body/booking_id, including the enum and default. The prose restates the 'customer or Civitatis department' target, which maps to the 'to' parameter but adds no syntax or format detail beyond 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 (write/send) and resource (message) plus scope: about one booking, to either the customer or the Civitatis booking department. An agent can distinguish this from sibling civitatis_list_messages or civitatis_get_booking without opening a 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 clear operational context: it reaches other people, so confirm with the user before each call, and the default confirmation can be switched off for this tool. However, it never names a when-not condition or an alternative tool (e.g., reading existing threads with civitatis_list_messages).

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