palace_estimate_cost

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

No annotations are provided, so the description carries the full burden. It adds useful calibration context ('calibrated on ~200 recorded Palace 0.16 runs') and output mode hints (quiet/typical/busy), but it does not state whether the tool is read-only, has side effects, or requires any permissions.

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?

The description is a single, information-dense sentence with no fluff, and it front-loads the core purpose. It could be slightly more structured for readability, but it is efficient.

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 14 undocumented parameters, no output schema, and no annotations, the description is far too sparse. It does not explain how the many optional inputs interact or what the estimation outputs look like, leaving an agent with substantial gaps.

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% for 14 parameters, and the description only loosely maps to three of them ('unknowns', 'config', 'tags'). The remaining parameters (e.g., tets, order, ranks, n_freq, eigen_n, problem, adaptive, calibration, solver_mode, n_excitations, ram_gb) are entirely undocumented.

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?

The description states a specific verb ('Estimate') and resource ('peak RAM and wall time') and notes both input modes (unknowns or config + tags). It is clear what the tool does, though it does not explicitly distinguish itself from siblings like palace_run or palace_results.

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?

There is no explicit guidance on when to use this tool versus alternatives. It implies estimation before running, but does not say 'use this before palace_run' or provide any conditions/exclusions.

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