Solve Capabilities

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

The description goes well beyond the readOnlyHint annotation by disclosing the side-effect-free resolution process: it executes nothing, installs nothing, and resolves binaries via env var -> PATH -> per-OS install dirs, and pip wheels by importability. It also explains the subtle distinction between a solver that resolves and one that is actually drivable, using SU2 as a concrete example. This is rich behavioral context that annotations alone do not provide.

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 long but densely informative, with a clear structure: purpose, side-effect-free guarantee, key gate to trust, return shape, and retention policy. It front-loads the most actionable information (pick a working solver) before diving into return fields. It loses one point because the return-shape enumeration is quite lengthy and could be trimmed or summarized without losing critical guidance.

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 zero-parameter capability-reporting tool with no output schema, the description is remarkably complete. It explains the return structure in detail, including the meaning of `any_available`, `prepared_case_only`, `toolsets.disabled`, and `cases` retention semantics. It even includes a user-facing pointer (point users at `cases.root`) and references issue #437. An agent has everything needed to call the tool and interpret its output correctly.

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?

The tool takes zero parameters, so the schema is trivially complete. The description explicitly states 'Takes no arguments,' which removes any doubt. The baseline for 0 params is 4, and the description earns it by confirming the no-argument contract and explaining what the tool returns instead.

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 opens with a specific verb ('Report') and resource ('P2 external solvers'), and immediately states the practical purpose: pick a working solver for a *_submit family instead of discovering availability by trial and error. It also explicitly names its sibling counterpart ('The solver twin of render_capabilities'), which distinguishes it from the render-related capability tool in the sibling list.

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 description explicitly tells the agent when to use this tool: before calling any *_submit family tool, to check solver availability. It also gives concrete guidance on how to interpret results, e.g., trust `families[*].any_available` as the gate, and tells the agent what to do when a family is under `toolsets.disabled` (tell the user its `enable` instruction rather than concluding the capability does not exist). This is explicit when-to-use and how-to-interpret guidance.

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