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

Annotations already declare idempotentHint=true and destructiveHint=false, and the description adds the concrete behavior behind those hints: repeating a call with the same idempotency_key returns the original project rather than creating a duplicate. It further discloses side-effect scope (no extraction, no credit consumption) and that the result surfaces a reviewUrl for browser-side PDF upload.

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 sentences, front-loaded with the core action and inputs, then constraints, then side-effect boundaries. Dense but every sentence carries distinct information; only minor tightening is possible.

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?

An output schema exists, so return fields need not be enumerated, yet the description still explains the reviewUrl's purpose. Combined with idempotency semantics, the trades precondition, and the explicit non-side-effects, an agent has enough to invoke it correctly; the only soft spot is that 'supported' metro_code is asserted without saying where valid codes come from.

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 description coverage is 0%, so the description must carry the load, and it does explain each parameter's role: name, trades (required for customer projects, sourced from preflight_takeoff), optional address, optional supported metro_code, and the idempotency_key's repeat-call semantics. It omits format constraints present only in the schema (length bounds, the key's character pattern) and doesn't enumerate trade values, but it compensates well beyond the baseline.

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 new construction estimate project') and names the source of its required inputs ('trades selection returned by preflight_takeoff'), which separates it from the sibling takeoff tools. The closing sentence 'Does not run extraction or consume estimate credits' explicitly demarcates it from run_takeoff.

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 prerequisites (trades required for customer projects, omissible only by the isolated synthetic reviewer) and routes the agent to preflight_takeoff for the trades selection. It also states the boundary condition for the tool itself ('Does not run extraction or consume estimate credits'), so an agent knows not to reach for it to start analysis.

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