attest

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

With no annotations, the description carries the full burden, and it does disclose the two fundamental modes and the destination of the artifact (Hedera mainnet vs. ~/.rubric/local-bundles/). It omits everything else an agent needs: whether mainnet anchoring costs money or takes time, that the operation is effectively append-only/irreversible, what permissions or key formats are required, and what the call returns.

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?

Two sentences, front-loaded with the action and immediately followed by the branch condition — very little waste. The terse "PQ-signed" jargon is unexplained, which costs a small amount of clarity for the compression gained.

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?

This is a state-changing tool with no annotations, no output schema, and three undocumented parameters, and the siblings (verify, get_proof) imply the caller needs a returned proof reference it never mentions. For that complexity, two sentences leave major gaps in return value, cost, and irreversibility.

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 0% across three parameters, including a free-form nested metadata object, so the description must compensate and does not. It says nothing about what payload should contain (raw text, JSON, a hash?), what agent_id identifies, or what metadata is persisted or exposed.

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?

"Attest an AI decision" gives a specific verb and resource, and the two sentences immediately split behavior into HCS-anchored vs. local Merkle leaf, which is concrete. It never names or contrasts the closely related siblings (verify, get_proof, attested_inference), so an agent must infer the boundary itself.

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 a real decision rule, but it is based on environment (presence of RUBRIC_API_KEY) rather than on task conditions. It never says when to attest versus when to call verify or get_proof, nor whether the local mode is a fallback or a deliberate choice.

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