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

Annotations already declare readOnly=false, destructive=true, idempotent=false and openWorld=true, so the safety profile is covered. The description still adds concrete consequences the annotations don't spell out: the estimate cannot be deleted via this API, duplicate calls create duplicate records, and it maps to POST /estimates. It omits auth requirements and what the response contains.

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?

Two dense sentences plus an endpoint token; the "WRITE:" prefix and the resource statement are front-loaded, and the irreversibility caveat follows immediately. Nothing is padded.

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 35-parameter mutation with no output schema, the description covers the mutation semantics well but leaves out what is returned (e.g., the new estimate ID) and how to retrieve the created record. There is also no mention of permissions or field-level constraints an agent would need before assembling a large nested payload.

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 46% across 35 parameters, so the description must compensate and does so only partially by enumerating payload sections (address, category, source, technicians, tasks, notes, products, services, other charges, tags). Many scalar fields — project, contract, phase, is_gated, gate_instructions, po_number — get no semantic clarification beyond their names, and the customer_name auto-create behavior lives only in 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?

Opens with a specific verb and resource ("WRITE: create an estimate (quote) for a customer") and enumerates the optional payload sections, so the scope is unambiguous. It does not explicitly contrast itself with create_job or create_customer, relying on the resource name to differentiate.

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 by the resource name — an agent knows this is the way to create an estimate — and the non-idempotency warning ("creating twice makes two estimates") tells it to check for duplicates first. However, there is no explicit guidance on when to prefer create_job versus create_estimate, or on prerequisites such as customer existence.

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