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

The description adds genuinely non-obvious behavior beyond the annotations: no email/notification side effect is triggered on the contact, and duplicate calls create duplicate records (consistent with idempotentHint=false). It does not cover permission requirements, validation failures, or what the response returns, so it stops short of full disclosure.

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 short sentences plus an endpoint reference, each carrying distinct information (mutation type, valid subtypes, no notification side effect, duplicate behavior). Front-loaded and zero 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?

Behavioral traits and the write classification are covered, and annotations already declare the safety profile so return-format detail is optional. However, for a tool with 10 loosely documented, all-optional parameters and a nested address object, the description gives no guidance on what fields make a usable contact, which leaves an agent guessing at call construction.

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?

With 10 parameters and only 10% schema description coverage, the description must carry the burden, and it barely does — the only parameter-related information is the 'Customer or Vendor' examples for the `type` field. Nine other fields (label, first_name, last_name, email, address nested object, etc.) and the question of a minimally valid create (zero required params) are left entirely unexplained.

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 contact') and enumerates the concrete subtypes it covers (customer, supplier, vendor), plus the underlying endpoint POST /contacts. The 'WRITE:' prefix and 'create' verb make it trivially distinguishable from siblings like list_contacts, get_contact, and update_contact.

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?

Usage is implied rather than stated: 'Creating twice makes two contacts' warns against duplicate invocation, and 'Nothing is emailed or sent' sets expectations, but there is no explicit 'use this instead of X' routing to update_contact for existing records or to list_contacts for lookup. An agent can infer when to use it, but the guidance is not spelled out.

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