kernel_outbox_list

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

With no annotations supplied, the description carries the full disclosure burden. It does add one valuable behavioral fact beyond the name: that approval cannot be performed through this tool and must happen in the dashboard. It omits other behavior an agent needs, such as ordering, pagination/limits, or what an empty result means.

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 clauses with the default filter front-loaded and the approval constraint second; nothing is padded. The parenthetical is terse to the point of introducing ambiguity about the default status value.

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?

There are no annotations, no output schema, and zero schema description coverage, so the description is the only source of parameter meaning and behavior — and it documents neither the project filter nor the actual effect of the status filter. For a tool this small, two sentences could have covered it; instead a key filter is undocumented.

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 explain both parameters and does not. The "default: pending" note is ambiguous because "pending" is not one of the enum values (draft, approved, sending, sent, rejected, failed), and the project parameter is never mentioned at all.

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 uses a specific verb and resource ("List outbox drafts") and implies a default filter, so an agent knows this is a read/enumeration tool over outbox drafts. It stops short of distinguishing itself from the named sibling kernel_outbox_propose, which is a plausible confusion point in an outbox workflow.

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?

"Approving happens only in the dashboard" is a genuine boundary statement that tells the agent not to look for an approve action here, which implicitly points at proposing/proposing-related siblings. However, there is no explicit when-to-use framing for the status or project filters, and no guidance on whether this returns all drafts or only the caller's.

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