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

The description goes far beyond the annotations: it explains the pending/confirmed lifecycle (~10 min), the non-idempotent behavior, that the gateway pays for the transaction, the 512-byte name cap, that the hash is stored exactly as given and never verified, and that metadata is public and permanent. This gives an agent a realistic model of side effects and constraints.

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 every sentence carries operational information: purpose, prerequisites, write mechanics, naming constraints, verification caveat, and size limits. It is front-loaded with the core action and record-name pattern, then layers necessary warnings in a logical order without fluff.

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 write tool with real-world side effects, the description covers prerequisites, rate limits, eventual consistency, naming constraints, data visibility, idempotency, and return values. The output schema exists, so not explaining the full return shape is acceptable; the description still mentions the record name and transaction id.

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?

Although the schema already covers both parameters, the description adds crucial semantics: content_hash becomes the record's suffix, should be a hex digest, and is not validated; metadata is stored verbatim, must stay under 20 KiB, and is public/permanent. This materially improves correct parameter construction beyond the schema text.

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 verb and resource: anchoring a memory/artifact on-chain as an NVS record with a precise naming pattern. It also conveys the tool's core value proposition (tamper-evident fingerprint) and clearly distinguishes it from siblings like read_record and register_identity by focusing on the write/anchoring action.

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 provides clear context for when to call it: after registering identity, with a signed-in OAuth session, and within the free-tier write limit. It implies the alternative flow (verifying later, likely via read_record) and states prerequisites, though it does not explicitly name when-not-to-use or list sibling exclusions.

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