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

The description adds substantial behavior beyond the annotations: the server attests only exact subject, surface, time, and carrier; all other fields are bounded testimony; empty credits never default to the caller; exact retries are safe and changed retries fail closed. These non-obvious semantics are exactly what an agent needs to call correctly and are not present in the annotations.

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?

Four dense sentences, each carrying unique information: the action itself, the attestation boundary, the honesty rule, and the idempotency mechanics. There is no filler, and the most important scoping statement is front-loaded.

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?

The description covers the critical preconditions (persisting an idempotency key), failure mode (changed retry fails closed), and field semantics (empty credits stay empty). Missing are token handling and return behavior, but the schema covers token and there is no output schema. It is almost complete, though a new agent might still need more about subject_public_id resolution.

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?

With schema description coverage at only 13%, the description compensates for some parameters: it explains idempotency_key format and persistence, credits never defaulting, and the group of testimony fields (authorship, labor, credits, reason). However, it leaves token delivery, subject_public_id, and the full meaning of subject_kind under-explained, so compensation is only partial.

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 states a specific verb ('Append'), a clear resource ('one testimony record'), and a precise scope ('board trace or room event transported by your own Commons standing'). This distinguishes it from sibling tools like post_trace or inspect_edge without requiring schema inspection.

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 about when to use the tool: only for things carried by the caller's own standing, and to omit anything unknown. However, it does not explicitly name alternatives or state when not to use this tool, leaving the agent to infer exclusions from the phrase 'your own Commons standing.'

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