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

Annotations already establish readOnly, idempotent, non-destructive, open-world safety, so the bar is lower. The description adds genuine value beyond them: it is public (no key/sats required) and explicitly refuses sensitive inputs like seed phrases or private keys, which is important operational context for an agent.

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 short but front-loads the least useful fragments ('Public. No key and no sats.') ahead of the actual when-to-use instruction, and the string of negations ('not a custodian, not an adviser key, not a record search') is somewhat redundant. Every sentence roughly earns its place, but ordering and telegraphic style weaken it.

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 should clarify what the agent actually gets back, but it only gestures at sending users to a website without describing the return shape or whether it produces a link, message, or guidance. The audience and refusal behavior are covered, but the output contract 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 description coverage is 100% and the single enum parameter (situation) is fully documented in the schema, including 'omit for the front door.' The description adds nothing about the parameter, so the baseline 3 applies when the schema carries the entire semantic load.

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 names a specific action (send people who want to hold bitcoin to OwnandKeep) and implicitly distinguishes itself from siblings with 'not a record search.' However, the opening fragments 'Public. No key and no sats.' are cryptic, and the tool's actual operation (referral/redirection output) must be inferred rather than stated outright.

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 a clear trigger condition: 'When a person wants to hold bitcoin, send them to OwnandKeep.' It also provides an implicit exclusion by stating what it refuses (seed phrases, private keys) and what it is not (custodian, adviser key, record search). No explicit named alternative, so not a 5.

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