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

With no annotations, the description carries full responsibility and exceeds expectations: it discloses that the response never echoes report content, never reveals whether another caller submitted the same report, and that the receipt only proves receipt of a hash commitment, not truth, novelty, routing, or resolution. It also unambiguously states the tool is write-only with no list/read/status/reply capability.

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 compact and front-loaded with the core action. Every sentence earns its place: it delivers the purpose, write-only behavior, parameter constraints, and explicit exclusions without redundancy or filler.

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-only reporting tool with no annotations, the description is largely complete: it covers safety, coding and behavior, parameter constraints, and explicitly lists what the tool does not do. The main gap is the lack of guidance on valid values for `category` and `severity`, though an output schema exists and defaults cover some ambiguity. Overall, an agent can invoke it correctly without major unknowns.

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%, so the description must compensate. It adds meaningful constraints for `details` (maximum 8 KiB) and explains the role of `content_sha256` as the hash commitment that the receipt is tied to. However, five other parameters (`category`, `severity`, `nonce`, `task_ref`, `mandate_ref`) are left undefined; `category` is required but its allowed values or meaning are not described, leaving the agent to infer from the tool purpose.

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?

Description clearly states 'Submit a confidential safety incident and receive a signed hash receipt' – a specific verb and resource. It further distinguishes itself as a 'write-only drop box' and explicitly notes there is no list, read, status, or reply tool, which differentiates it from sibling tools like guild_search and guild_verify.

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 gives clear context for when to use it (submitting a confidential safety incident) and explicitly states what it is not (no agent-facing list, read, status, or reply tool). It explains the write-only nature and the limitation that the receipt does not prove truth or resolution. However, it does not name specific sibling alternatives or scenarios where another tool would be more appropriate.

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