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

With no annotations, the description carries the full burden and delivers exceptional disclosure: "THIS SERVER NEVER SEES YOUR KEY and never signs" states the security model, "it hands back bytes, and you sign the digest wherever your key lives" clarifies the external-signing workflow, and "it builds the transaction either way" plus "If the verdict says refused, broadcasting will cost a fee and fail" disclose the unconditional-build behavior and its failure consequence. These are exactly the non-obvious behaviors an agent must know before invoking the tool.

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 four sentences with the core action front-loaded in the first sentence and every subsequent sentence carrying a distinct behavioral fact: security model, unconditional build, and failure consequence. There is no filler, repetition, or tangential content; the emphatic restatement of the no-signing policy reads as reinforcement rather than redundancy.

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 complex tool with 7 parameters, two nested objects, no output schema, and no annotations, the description covers the critical ground: what it produces (digest bytes plus advisory verdict), the security posture, and the fee/failure outcome of a refused verdict. The only meaningful gap is the absence of a precise return contract (exact shape of the digest and verdict), which no output schema exists to supply; the rich schema documentation partially offsets this by explaining input semantics in depth.

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 100%, with rich parameter-level documentation already present (stale-UTXO warning, reserveRoot delegation rule, fee mass rationale, allowlist requirement for recipient, computeBudget over/under-provisioning tradeoff). The description itself adds no parameter-specific meaning, but per the baseline rule for high coverage, it need not. The schema handles parameter semantics; the description handles behavior.

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 and resource: "Assemble an unsigned Kaspa transaction that spends from this grant, and return the digest to sign." This clearly marks it as the payment-building tool among siblings named build_delegation, build_exit, and build_settlement, and its focus on producing a digest for external signing differentiates it from the check_* tools. The output type (digest bytes) is explicit, leaving no ambiguity about what the tool produces.

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 conveys implied usage context: it bundles the advisory verdict with the build and explains that the build happens regardless of local rules, signaling that this is the tool to use when you actually want a spend transaction constructed rather than merely vetted. However, it never names an alternative (e.g., warda_check_spend for advisory-only checks) nor gives explicit when-to-use/when-not-to-use routing, so the agent must infer the division of labor from sibling names.

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