is_realizable

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

With readOnlyHint and idempotentHint already declared, the description still adds real value by disclosing outcomes: a realizable verdict, or unrealizable plus the environment's counter-strategy, plus the unrealizable core when core=true. It omits what timeout does on expiry and how large the counter-strategy output can be, so behavioral disclosure is useful but incomplete.

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-loads the tool identity and the realizability question, then adds prerequisites and return behavior in a compact block. Line breaks are slightly awkward but every sentence carries information; nothing is wasted.

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?

There is no output schema, and the description appropriately covers the possible return outcomes and the core variant, which is what an agent most needs. The main gap is the undocumented timeout parameter and the absence of any note on what the counter-strategy looks like or how it is returned.

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 description coverage is 0% at the parameter level, and the description only explains the core flag ("with core, also the unrealizable core"). timeout's behavior is never described, and the contract object is covered only indirectly via the GR(1)/slugs constraint, so the description fails to fully compensate for the coverage gap.

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?

Names the specific check (GR(1) realizability via slugs) and states the question it answers in one precise sentence: can a component choose outputs so guarantees hold for every environment satisfying assumptions. It also distinguishes itself from the sibling unrealizable_core, which is the narrower core-only operation.

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?

Gives concrete prerequisites ("Needs slugs; the formulas must be in the GR(1) fragment") and points to unrealizable_core when only the core is wanted. It does not explicitly say when to pick this over is_consistent, is_compatible, or synthesize, so the alternative-routing is partial rather than complete.

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