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

With no annotations, the description carries the full burden. It discloses that the tool is non-persistent ('never persists'), non-replacing ('never replaces...'), and explains the criteria for a CONFIRMED verdict ('real verification that HELD, an INDEPENDENT witness (witness != author), and the wait'). It could add more detail on error handling or side effects, but it is quite transparent for a gate tool.

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 dense but efficient, with three sentences covering purpose, decision criteria, and limitations. Key terms like 'REJECT / QUARANTINE / CONFIRMED' are front-loaded. The reference to 'covenant rule 8' adds context but is slightly esoteric; still, every sentence contributes to understanding the tool.

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 tool with 10 parameters and no output schema, the description explains the output format ('verdict plus the nine-field record') and the key behavioral constraints. It doesn't detail the nine fields, but it provides enough for an agent to know what to expect. The distinction from kernel and consent_check is partially addressed through the non-persistence and non-replacement statements.

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 coverage is 70%, so the description is not solely responsible for parameters, but it does add valuable semantics. It connects witness independence to the CONFIRMED condition, ties evidence to a 'verification that HELD,' and mentions 'the wait' (likely wait_satisfied). It does not explain all 10 parameters, but it highlights the ones that affect the verdict, going beyond the schema descriptions.

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 clearly states the tool's function: 'Route ONE proposed state-change through the kernel and get back the verdict (REJECT / QUARANTINE / CONFIRMED) plus the nine-field record.' This includes a specific verb, resource, and output. It also distinguishes itself from sibling tools by noting it 'never persists and never replaces the signature / consent checks on the real write.'

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 for when to use the tool: 'so you can DISCERN before you write.' It also gives an explicit exclusion: 'it never persists and never replaces the signature / consent checks on the real write.' This tells the agent when not to rely on it. However, it does not explicitly name alternative tools or provide a full when-to-use vs. when-not-to-use list.

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