palace_build_config

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

With no annotations, the description carries the full burden and does disclose two behavior-affecting traits: the specific safe defaults silently injected (MUMPS, direct solve for eigen/small driven, cheap estimator, Excitation = Index) and the conditional write triggered by 'out'. It omits overwrite semantics and error behavior on an invalid spec, which keeps it out of the top band.

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?

One dense sentence with no filler; the purpose is front-loaded and the defaults, write condition, and return values follow in priority order. Slightly overloaded by the parenthetical default list, but every 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 a 4-parameter generator with no output schema and no annotations, the description covers the essential decision inputs: what it produces, the defaults it silently applies, when it writes to disk, and that it returns lint plus schema results. Gaps on ram_gb/palace_version semantics and overwrite behavior are the main omissions.

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 50%: out and spec are documented, while ram_gb and palace_version are undocumented in both schema and description. The description compensates partially by enumerating what the spec contains (physical-group names, units, ports, sweep), which adds meaning over the schema's generic 'spec dict or path to a JSON file'.

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+resource: 'Build a Palace JSON config from a compact spec', with the input form (physical-group names, units, ports, sweep) made concrete. It is clearly a generation tool distinct from lint/run siblings, but it never names or explicitly contrasts an alternative, so it stops short of full sibling differentiation.

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 conditional 'Writes it if "out" is given' gives real usage signal about when the tool persists output versus only validates. However, there is no explicit when-to-use guidance relative to siblings like palace_lint_config or palace_run; the workflow context (build before run) must be inferred.

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