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

Annotations only say readOnly=false, destructive=false, idempotent=false, openWorld=true; the description goes well beyond them by stating the return is 'a durable receipt and duplicate flag, not a promise of a fix,' that 'no code or production behavior changes automatically,' and that the server cryptographically checks a signed quote against Verity's published keys. It also discloses how to check status afterward via GET /api/index/v1/feedback/<id>, which is real operational context an agent cannot infer from 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?

Purpose and the submission gate are front-loaded, and nearly every clause carries information. The quote sentence, however, is a long semicolon-chained run that is harder to parse than it needs to be, and could be split without losing content.

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 write tool with an output schema, the description covers the essentials: privacy constraints, side-effect profile, duplicate/receipt semantics, and follow-up status lookup. The remaining gap is that it never characterizes the required report fields or the surface enum, though the enum values are self-describing tool/endpoint names.

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 description coverage is 0% across 9 parameters, so the description must carry the load. It does this well for the nested quote object, naming price, at, source, grade, signature and kid and explaining why the signature matters, but it says nothing about the five required core fields (category, surface, expected, actual, reproduction) or about symbol, requestId and observedAt, leaving half the surface undocumented.

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 verb and resource: 'Write one structured bug, missing capability, or data quality report for private human triage.' That instantly separates it from every sibling, which are all read-only lookup tools (get_index_price, verify_print, list_index_assets), and it names the three report categories the tool accepts.

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?

It gives an explicit gating condition — 'Only submit when the user requests reporting' — plus concrete exclusions ('do not include keys, passwords, transcripts or attachments') and a conditional branch for price problems that tells the agent exactly which extra fields to add. There is no competing sibling for reporting, so the absence of a named alternative is not a gap.

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