palace_check

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

No annotations are provided, so the description carries the full behavioral burden. It does not say whether this reads files or executes a solver, whether it mutates anything, what permissions or a completed run it requires, or what happens on failure. Listing check names is not the same as disclosing behavior.

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?

A single front-loaded sentence with no filler, but it is an undifferentiated comma list of jargon that would benefit from grouping or structure. It is compact without being genuinely well organized.

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 tool with 7 parameters (including nested objects), no annotations, and no output schema, the description is far too thin. It neither documents inputs nor clarifies what a check result looks like, leaving the agent unable to invoke it confidently.

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?

Seven parameters with 0% schema description coverage and no descriptions, and the description names none of them explicitly. There is only a loose implicit mapping (e.g. 'eigenmode at the expected frequency' ↔ expect.eigen_ghz, 'convergence' ↔ convergence, 'port symmetry' ↔ symmetric_pairs), leaving config, case_dir, output_dir, and reference_touchstone entirely unexplained.

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 gives a specific verb ('Sanity checks') followed by a concrete list of checks (passivity, reciprocity, energy balance, port symmetry, eigenmode, log errors, spurious modes, convergence), so an agent can infer the domain. But it never states what artifact it operates on (a case dir, results, a config) and does not distinguish itself from siblings like palace_lint_config, palace_lint_rules, palace_doctor, or palace_status.

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?

No guidance on when to run this versus the numerous sibling lint/doctor/status tools, no prerequisites (e.g. must a simulation have completed first?), and no statement of when it is not appropriate. The list of checks implies a post-run validation context but the agent must guess.

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