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

Adds real behavioral context beyond readOnlyHint=true: the result contains a `display` markdown field with chan images that must be shown to the user, secrets never leave the machine, and there is a warning against scams. Some of this is instructional/emotional rather than mechanical, capping it below 5.

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?

One giant run-on sentence mixing scope, security warnings, chain notes, and follow-up pipelines. Front-loading is weak and the wallet/path enumeration dominates the length without earning its space since the schema already enumerates branches.

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 single-param, no-output-schema playbook tool, it conveys what's returned, how to display it (`display` markdown with images), and the follow-up pipeline (find_money -> verify_tx -> human signs -> broadcast_tx). Enough for an agent to use it 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?

Schema coverage is 100% and the `situation` enum is fully described in the schema. The description repeats 'one branch via situation=' and implies branching but adds no format guidance beyond the schema. Baseline 3 applies.

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 clearly what it returns: the complete recovery playbook, with an enumerated list of wallet types and derivation paths covered. Distinguishes itself from signing_guide by noting it's 'Step 1 of signing_guide, also callable alone.' Slight deduction because the one-sentence purpose is buried under a dense enumeration.

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?

Explicitly says it can be called alone or as Step 1 of signing_guide, and points to swapchan_playbook for workflow context (recover-old-wallet). Lacks explicit 'do not use for X' exclusions, but the alternatives context is clear.

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