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

Annotations already declare readOnly=false, destructive=true, idempotent=true and openWorld=true; the description adds genuinely new context (an owner-approval prerequisite and the rule that self-reports can't confer verified evidence status). It does not explain what the destructive hint actually affects or what the resulting record state looks like, so it goes modestly beyond the annotations without fully carrying the burden.

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 tight sentences with no filler, and the core action is front-loaded before the constraint. Every sentence carries information.

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 16-parameter, 9-required mutation with nested objects and enums, no output schema, and zero schema descriptions, the description is far too thin. It conveys intent and one policy rule but leaves the agent without the detail needed to populate a complex publish payload.

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 16 parameters (9 required, nested objects, 3 enums), so the description would need to compensate heavily. It supplies no parameter-level meaning at all – fields like conditions, sources, record_kind, occurred_at, visibility and idempotency_key are entirely undocumented anywhere.

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 gives a specific verb (submit) and resource (an owner-approved minimal outcome or failure), so the core action is clear. It does not, however, distinguish this publish operation from siblings like create_request or report_reuse, leaving the agent to infer the boundary.

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?

'owner-approved' signals a precondition, and the note that self-reports cannot assign verified evidence status hints at limits. But there is no explicit when-to-use/when-not framing and no named alternative among the sibling tools, so usage is only implied.

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