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

Annotations already declare a non-readonly, open-world, non-idempotent, non-destructive mutation. The description adds real context beyond that: the company writes the quote itself, delivery goes to the client over WhatsApp or e-mail when supplied, and the agent should tell the client so. It doesn't touch duplicate submissions or failure modes, so it stops short of a 5.

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 scope and the routing to find_companies/list_services are front-loaded, and the fallback to book_appointment comes after the primary path. It is dense and long for a single call, and the terse '— say so' instruction costs a moment of parsing, but no sentence is pure 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 10-parameter mutation with a nested answers object and no output schema, the description covers the full pre-call chain (select company, select service, confirm with client) and the alternative flow. What it omits is what the call yields — a request identifier the agent would need for get_request_status — leaving the post-call step unstated.

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 90% schema coverage the baseline is 3; the description still adds meaning by tying `company` to the find_companies result, restricting `service` to quote-request bookings from list_services and noting it may be omitted when only one exists, and noting photos and e-mail are optional/conditional. The nested `answers` object is left 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?

The description states a concrete verb and resource — it sends a job description, contact data and photos to a chosen company so that the company itself writes a quote. It explicitly separates this from fixed-price work and names the sibling escape hatch (book_appointment with an «assessment visit» service), so an agent can tell it apart from get_quote and book_appointment.

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?

It gives explicit preconditions (company chosen from find_companies, only after the client confirmed the description and contact), the required service selection rule ('required when it lists more than one'), and a named alternative path for companies without a quote-request service. When-to-use and when-not-to-use are both present.

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