Red-Team Plan Grilling

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds that the analysis is automated and framed around four specific adversarial lenses, which is genuine behavioral context, but it omits whether this registers a cognitive gate, how the sessionId interacts, or what the response contains.

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?

A single efficient sentence with the key concept front-loaded and no padding. It is compact, though the density of unexplained proper-noun lenses makes the concision partly cosmetic.

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 an 8-parameter tool with only one required field and no output schema, the description is thin: it does not explain the return shape, the effect of depth levels, or how sessionId/decision_narration integrate with the broader workflow. Annotations and the rich schema cover safety and inputs, so the gaps are moderate rather than severe.

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 88%, so the schema already documents plan, depth, label, context, sessionId and the narration fields. The description adds nothing about any parameter — notably the depth enum and the mandatory narration/label requirements are left entirely to the schema. Baseline 3 applies.

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 verb phrase 'adversarial stress-testing' plus the named lenses (Inversion, Simplification Cascades, Blast Radius, Edge-cases) gestures at red-teaming a plan, but the description never explicitly states that the input is a plan or what the output is. No sibling is named or contrasted, and the four lenses are unexplained jargon an agent cannot act on directly.

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?

There is no statement of when to call this versus e.g. kilo_trace_root_cause, kilo_benchmark_solution, or kilo_think_step, nor any exclusion or prerequisite. The 'depth' param (quick/deep/hardcore) implies graduated use but the description never routes the agent.

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