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

With no annotations, the description carries the full burden and does well: it discloses the return shape (score, prioritised findings with fixes, improvement ideas), the screening-not-certified limitation, and a per-call cost of 1 credit. It does not state runtime or failure behavior, but coverage of the key behavioral traits is strong.

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?

Front-loads the purpose, then packs the input list densely, and closes with return description, disclaimer, and cost. The parameter enumeration is a long run-on block, but every clause carries information given the 21-parameter surface.

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 21-param, no-annotation, no-output-schema compute tool, the description supplies purpose, input semantics, return contents, scope limitation, and cost. Only gaps are the two undocumented fields and absent guidance on partial-input behavior nuances.

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 0%, so the description must compensate, and it does: it enumerates and explains nearly all 21 inputs with structure, units, and per-field meaning (tributary_width_m, egress_window, ventilation, zone enums). It omits shear_walls and aspect_ratio, so it is not fully complete.

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: screening an existing building design for weaknesses and improvements, plus a 'stress-test' title. It implicitly separates itself from the design-oriented sibling arch_design via 'existing project', but never names an alternative explicitly.

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 useful invocation context ('provide whatever you have', all inputs optional) and a scope caveat ('screening only, not a stamped engineering check'). However, it offers no explicit when-to-use-vs-alternatives routing against arch_design or other siblings.

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