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

Annotations already declare readOnly, non-destructive, non-open-world, and notably non-idempotent behavior, but the description adds real context beyond them: it discloses the return shape (model-scoped verdict plus portable Ed25519 server receipt), scopes what the verdict does not certify, and states the failure mode ('native failures return no scientific verdict'). The 'bounded native engine' phrasing hints at resource limits. It does not explain the surprising idempotentHint=false, which is the one remaining gap.

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 purpose, then return value, then scope caveats, then the route-claim distinction and failure mode. Each sentence carries information, though the trailing docs pointer is a slightly inert way to end.

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?

With no output schema, the description correctly takes on the burden of explaining the return (verdict + receipt) and the failure case, which it does. For a nested, 3-parameter tool at 0% schema coverage, the in-line guidance on the free-form parameters object is thin, kept afloat by a documentation pointer.

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%, so the description must carry the load, and it largely defers instead ('Parameters and examples: /verify and /docs/mcp/'). It gives useful semantics for the domain enum and clarifies that route claims distinguish 'optimality' from a supplied tour total (mapping to claim.kind), but the free-form 'parameters' object and the rest of the claim structure are left 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?

States a specific verb (verify) and resource (structured arithmetic, shadow, ephemeris, statistics or route claim), and enumerates the domains it covers. This distinguishes it from single-domain siblings like check_arithmetic, check_ephemeris, verify_shadows and route_optimizer, which an agent can separate without opening any schema.

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 domain list implies when the tool applies (multi-domain structured claim verification), and it clarifies what the tool is NOT for ('never truth, authenticity or fraud certification'). However, it never explicitly says when to prefer this unified verifier over the domain-specific check_* / verify_shadows siblings, leaving routing to inference.

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