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

Annotations already declare read-only, idempotent, open-world, non-destructive, so the bar is lower, yet the description adds substantial behavioral detail: it fetches the record from the ledger and the key from a /.well-known endpoint (explaining the openWorldHint), then recomputes five explicit checks — hash match, closed shape, key listing for heights, Ed25519 verification, and anchor status. It also states the negative guarantee that no content, scope, or answer text is present, which matters for a verifiability tool.

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?

Front-loaded with the return value, then the inputs, then the verification pipeline — a sensible order. The middle sentence is long and compiler-dense ("the shape is closed, the key is listed for the record's heights"), but every clause carries real information rather than filler.

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?

An output schema exists, so return-value detail needn't be spelled out, and the description covers provenance, verification steps, and content-exclusion. What's left implicit is failure behavior — what happens if the record is missing or a check fails — which matters for a verification tool but is arguably carried by the output schema.

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%, so the baseline is 3. The description restates what the schema already says (sha256 as canonical hash, day used when sha256 is absent) and adds only the minor detail that the day lookup goes through the runner's day status. No precedence rules beyond the schema's own wording, no format examples beyond YYYY-MM-DD.

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 a specific verb and resource: "Return the day record (furui-check-day-v0)" and enumerates its contents (signed RFC 6962 root of one UTC day's check envelopes plus their count). An agent knows exactly what comes back. It does not distinguish itself from siblings such as nenrin_furui_leaf or nenrin_ledger_entry, so the sibling boundary must be inferred from the name.

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 gives invocation paths — "Give its SHA-256, or a day (YYYY-MM-DD)" — and notes the day path resolves "through the runner's day status." That is lookup guidance rather than when-to-use guidance: it never says when this day-level record is the right tool versus the leaf-level or ledger-entry siblings, nor what to do when neither identifier is known.

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