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

The annotations object is empty, so the description carries the full burden. It does disclose that the return value is a highly sensitive secret recovery phrase and that the owner should be made aware of it, which is meaningful behavioral context for a security-critical read. It omits permission requirements, whether the call is auditable/logged, any rate limits, and confirms no annotations to fall back on.

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 opening sentence is duplicated verbatim, which is pure waste, and the legacy @param/@return tag block is a loose structure rather than front-loaded prose. The purpose is first, which saves it from a 1, but the redundancy signals low editorial quality.

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 tool that emits seed material there is no output schema and no annotations, so the description should carry the load; instead it reduces the return to 'a json object'. It covers parameter provenance but says nothing about the response shape, security requirements, or failure modes, leaving real gaps for a high-stakes operation.

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 compensate, and it largely does: it documents all three params, stating api_key is the application's allocated key and that token and wallet_fk both come from /access/login. That provenance detail is exactly what the schema lacks. It stops short of 5 because types and formats are not restated beyond the schema.

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: it returns the wallet's 24-word mnemonic phrase. That is unambiguous and unique among the ~120 siblings, none of which expose seed material. It does not, however, name or contrast any sibling tool, so it stops short of the 5 tier.

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 'for future secret recovery' framing hints at the scenario (seed backup/recovery), and the note about informing the wallet owner implies a handling context. But there is no explicit when-to-call guidance, no prerequisites (e.g. required PIN/2FA state), and no when-not-to-call condition.

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