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

Annotations already declare readOnly=false, destructive=true, idempotent=false. The description adds value beyond them by disclosing the myId uniqueness rule ('if myId already exists nothing is created and an error is returned') and the underlying endpoint (POST /site/send). It does not explain the error shape or what happens to the partial creation, but with strong annotation coverage this is a solid additive block.

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?

Three tight sentences, no filler, and the operation class plus core requirement are front-loaded. Every sentence carries either purpose, prerequisite, or a behavioral rule.

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 write tool with a nested customer object and no output schema, it covers the essentials (required fields, uniqueness behavior, endpoint) but is silent on the return value, on the optional contact/addressComplement fields, and contains a mild mismatch about address being required.

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 56%, so the description partially compensates by naming name, address, customer (id or myId) and the my_id collision semantics. However it says an address is 'needed' while the schema marks only name and customer as required, and the six contact/addressComplement fields are undocumented in both places.

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+resource ('create a new site') and immediately disambiguates the resource's domain meaning ('a location of a customer'), which separates it from sibling create_customer and from get_site/list_sites. The 'WRITE:' prefix signals the operation class up front.

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?

Conveys prerequisites (needs a name, an address and the customer), which is implicit usage guidance, but never states when to choose this tool over alternatives or what must exist beforehand (e.g. the customer must already exist). No exclusions beyond the myId collision case.

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