submit_verification_observation

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

No annotations are provided, so the description carries the full burden. It does disclose one genuinely useful behavioral trait — that MangoMe 'does not execute the check itself,' i.e. this only persists an observation rather than performing verification — plus a REPLAY/RB/1 precondition. But it omits auth requirements, whether persisted observations are immutable, failure behavior, and other traits expected of a write tool with no annotation support.

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 short sentences with no padding, and the core action is front-loaded. The efficiency is undercut only by unexplained jargon that forces the reader to look elsewhere for meaning, but structurally it 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?

An output schema exists so return values need not be described, but the definition remains incomplete: 14 parameters, 9 required, with zero schema descriptions and nothing in the prose; no annotations; and heavy unexplained domain jargon (AV/1, RB/1, MangoMe, REPLAY). An agent lacks enough to invoke this reliably.

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?

14 parameters with 0% schema description coverage, and the description explains none of them. It doesn't clarify the roles of verifier_token, verifier_actor_id, observation_type, evidence_type, evidence_class, status, or the optional details/reproduction objects. With no annotations and no parameter prose, the description fails to compensate for the coverage gap.

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 ('Persist ... verifier observation'), so the basic action is identifiable. However, the AV/1 qualifier is unexplained jargon, and nothing distinguishes this from nearby siblings such as verify_slice, submit_evidence, attest_evidence, or record_truth_assertion. Purpose is clear-ish but not distinguishable within its family.

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?

There is no explicit when-to-use or when-not-to-use guidance and no named alternative. The line about REPLAY requiring an intact RB/1 binding hints at a precondition, but it is opaque and does not tell the agent which sibling to call instead or under what circumstances this tool applies.

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