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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral depth beyond these: explains mode-specific processing (parses fields, checks signature and expiry), states 'Recovery only — FlexYield never holds keys' for security reassurance, and notes 'Read-only' and API key requirement. This adds context without contradicting annotations.

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 long but each sentence earns its place: it leads with the core purpose, then explains modes, gives usage and exclusions, details return values, and ends with security and requirements. It is dense but not verbose; no filler. Structure is logical and front-loaded.

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 with two distinct modes and no output schema, the description is thorough: it covers input semantics per mode, expected return fields, authentication needs, and explicitly scopes what the tool does NOT handle (binding, hashing, domain/nonce policy). All essential information for correct invocation is present.

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?

Despite 100% schema description coverage, the description enriches parameter meaning: it explains that mode 'personal' verifies an EIP-191 personal_sign signature, while 'siwe' verifies SIWE/EIP-4361, and clarifies the signature is 0x-hex 65-byte (r‖s‖v). It also specifies the address is optional in personal mode. This goes beyond the bare schema properties.

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 specifies the verb 'verify' and the resource 'signature' with two distinct modes (personal/SIWE), and explicitly contrasts with sibling tools: 'Not for binding or claiming keys... use bind_key_complete / claim_agent_complete' and 'not for hashing (use convert_evm)'. This unequivocally clarifies what the tool does and how it differs from related tools.

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 direct usage guidance: 'Use it to authenticate a wallet-holder or validate a login message' and then lists exclusions with alternatives. It also notes 'domain and nonce policy stay with you,' indicating when the tool does not handle those aspects. This is explicit when-to-use and when-not-to-use guidance.

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