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

Annotations only tell the agent this is a non-read-only, non-destructive, non-idempotent call; the description adds that the result is anchored on Base L2 with evidence_hash and base_tx_hash, and that the artifact expires in 72 hours. That on-chain anchoring and TTL context is real value beyond the annotations. It does not mention cost/gas implications or what happens if a duplicate proof is requested (relevant given idempotentHint=false).

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 first three lines are front-loaded and dense: purpose, outputs, prerequisite, expiry. The trailing Args block duplicates a schema that is already 100% documented, which is wasted surface area, but the rest of the description is tight.

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 mutation tool that issues a short-lived on-chain-anchored proof, the description covers the trigger condition, the dependency on mt_endorse_agent, the return hashes, and expiry, and an output schema exists so result shape need not be spelled out. Minor gaps are the absence of cost, error/retry behavior, and whether the proof is bound to one specific agent pair.

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 100% and the Args block in the description repeats the schema text almost verbatim, so no new meaning is added for any of the five parameters. The one useful implication — that outcome and interaction_type are constrained to a small value set — is conveyed only as examples, and no enum is enforced in the schema.

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 ("Create an interaction proof") and immediately ties it to a downstream consumer, SkillEndorsementCredential, which separates it from the many mt_* verify/issue siblings. It does not differentiate itself from adjacent proof/evidence tools (moltproof_evidence, molcheck_evidence), but the operation itself is unambiguous.

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?

"Required before calling mt_endorse_agent" gives an explicit ordering constraint and names the alternative that depends on it. "Valid for 72 hours" tells the agent the proof is short-lived and shouldn't be cached indefinitely. It stops short of saying when not to use it or how to refresh an expired proof.

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