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

The description goes well beyond the annotations: it discloses that verify costs simulation, that the exact search refuses past a 1,000,000 refinement-step budget on large/symmetric nets, and that it falls back to a sampled permutation experiment. The one gap is that destructiveHint=true is never explained — nothing says what is mutated or destroyed (presumably the annotation slots), so the safety profile is left to the annotations alone.

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-loaded with the core action and return shape, and every clause carries information (annotation slot scope, verify behavior, budget, caveat pointer). It is dense and parenthetical-heavy, which slows parsing slightly, but there is little outright waste.

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 no output schema and three parameters, the description covers what is returned (JSON-LD with empty annotation slots), the mutation contract ('nothing else'), and where to find the full colour-refinement caveat and annotation contract. It is nearly complete; only the destructiveHint implication is left implicit.

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 100%, so the baseline is 3, but the description genuinely enriches verify beyond the schema by explaining the exact-proof vs sampled-experiment distinction and the budget cutoff. inline_context and id merely restate what the schema already documents in detail.

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: 'Discover the parameter classes of a stored model and return them as JSON-LD with empty annotation slots.' It also clarifies what the tool does NOT do ('membership/kind/evidence are derived and settled by measurement, not yours to edit'). It never names a sibling tool to differentiate itself, so it stops short of a 5.

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?

It gives conditional guidance for verify=true (exact proof where the search can decide, sampled experiment as fallback) and points to a resource for the annotation contract. However, it never states when to use this tool versus siblings like sim_propose_types or sim_param_heatmap, and offers no exclusions. Usage is implied rather than spelled out.

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