attest_agent_output

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

The description discloses key behaviors: server-side envelope construction, hashing, anchoring, immediate async response with {jobId, status}, polling requirement, and the trust model ('without trusting this server'). It omits details like fees or permission requirements, but since no annotations exist, this is a solid disclosure of core behavior.

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 two dense sentences that front-load the core purpose and then concisely explain the async flow. Every clause adds essential information without redundancy.

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?

Given the tool's complexity (12 parameters, async, no output schema), the description explains the initial response, the polling action, and the eventual deliverable (envelopeJson). It is slightly ambiguous about which response contains the envelopeJson, but overall it is sufficiently complete for an agent to use it.

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?

The input schema covers 100% of parameters with meaningful descriptions, so the baseline is 3. The description adds conceptual mapping (agent X, output O, input I, time T) but provides no additional parameter-level guidance beyond what the schema already offers.

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 opens with a specific action: 'Anchor agent-output provenance on the Midnight chain' and elaborates with the semantic 'agent X produced output O from input I at time T'. This clearly distinguishes the tool from siblings like verify_attestation and anchor_document.

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: it is async, returns a jobId/status immediately, and instructs polling get_job_status until completion. It also mentions that third parties can verify via verify_attestation. However, it does not explicitly state when not to use this tool or name alternative attestation/document tools.

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