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

Because there are no annotations, the description carries the full burden and does a good job: it discloses the compound behavior (creates watch + returns quote), the grace credit activation, the automatic credit on payment confirmation, and the return value ('Returns the FREE endpoint + body to call'). This goes beyond the schema to explain the sequence of events. It stops short of discussing failure modes or permissions, but the core behavioral traits are clearly transmitted.

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 tight sentences, each delivering a distinct piece of information: purpose, activation/credit behavior, return value, and defaults. It is front-loaded with the main action and differentiator. There is no filler, and even the repetition of 'no USDC, no EVM wallet' reinforces the critical contrast. This is highly efficient.

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, no annotations, and no output schema, the description covers many non-obvious behaviors: the combined watch+quote flow, grace credit, automatic credit, defaults, and a pointer to external bounds. The phrase 'FREE endpoint' is slightly ambiguous (free of charge? no authentication?), and error conditions are unaddressed, but overall the description is largely complete for an agent to invoke 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 schema has 100% coverage, so the baseline is 3. The description adds value by explaining the default for `payWith` ('pay in the coin you are watching') and the default for `amountUsdCents` ('buy the policy minimum of credit'), which are not obvious from the schema. It also directs the agent to `*_private_watch_info -> crypto_topup` for bounds, enriching parameter understanding.

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 the exact action ('POST /v1/private/watch-crypto creates a Monero/Zcash payment watch AND returns a coin payment quote in one call') with a specific verb and resource. It immediately differentiates from the sibling tool `seneschal_private_watch_create` by explicitly saying 'no x402, no USDC, no EVM wallet anywhere in the flow.' The title reinforces this distinction, making the tool's purpose unmistakable.

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 positions this as 'The all-coin onboarding path' and implies when to use it by negating the EVM/USDC flow. It provides clear context about defaults ('pay in the coin you are watching, buy the policy minimum of credit') and points to `*_private_watch_info -> crypto_topup` for bounds. However, it does not explicitly name the alternative tool for USDC/EVM, so it's slightly below the 'explicit when/alternatives' bar.

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