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

With readOnly/idempotent/non-destructive annotations already covering the safety profile, the description adds real behaviour: the precedence rule (hours typed on the line, else a rate band for its quantity, else the reason for none), the crew-days computation, and the explicit 'Hours only: no prices' scope limit. It still doesn't say what happens when no source argument is supplied, which matters for a tool with zero required parameters.

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 with the output stated first, then the computation precedence, then the scope exclusion — front-loaded and waste-free. The compressed phrasing ('else the reason for none') is dense but each clause carries information.

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 an 11-parameter tool with deep nested objects, the description suffices: it says what is produced, how each line's hours are derived, and that prices are excluded, while the output schema covers the response shape and annotations cover safety. The one real gap is that no-argument behaviour is never described, despite every parameter being optional.

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 100%, so all 11 parameters are already documented individually and the baseline of 3 applies. The description's source list is ordered as alternatives ('a token, a file, calculators, takeoffs or a drawing'), hinting at mutual exclusivity the schema never states, but it adds no guidance on combining or omitting them.

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?

It names the exact computed quantity ('Estimated person-hours on each line of a project') plus the secondary output (the project's crew-days), so the resource and result are unambiguous. 'Hours only: no prices' draws a boundary against pricing siblings, but neither that nor any other tool is named.

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?

The sentence 'From a token, a file, calculators, takeoffs or a drawing' implies which inputs are accepted and that they are alternatives, which is useful routing. However, there is no explicit statement of when to call this instead of calculate, run_takeoff, estimate_house or create_project_file_from_* — the boundary with siblings is left to inference.

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