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

With no annotations provided, the description carries the full behavioral burden. It discloses the return shape ({rule, threshold, status, evidence?}), enumerates the possible status values, and signals pure derivation behavior through 'derive' and 'returns'. It could go further by explaining how thresholds or statuses are decided, but the provided behavioral and output information is substantial for a compute-style 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?

Three sentences with no filler. The main action and inputs are front-loaded, then the return format, then a purposeful note about why prose criteria are inferior. Every sentence contributes necessary information, and the structure is easy to scan.

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 three inputs, no annotations, and no output schema, the description covers the key invocation details: what it does, what inputs it expects, and what it returns. It does not define the semantics of 'tripped_now / monitor / cleared' or how thresholds are determined, but it gives enough shape for an agent to call it correctly and interpret the result at a high level.

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 67%, and the schema descriptions for unitEcon and dealbreakers are minimal ('The result of ...'). The description adds meaning by naming the upstream tools and framing all three inputs as 'upstream signals'. It also gives meaning to icpDriftCount as an 'ICP drift count', which the schema lacks. This compensates for the schema gaps and helps the agent understand what to pass.

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 states a specific verb ('Derive') and resource ('a falsifiable, data-driven list of kill criteria') and clearly identifies the upstream inputs. It also differentiates itself from siblings by naming two upstream tools and explicitly contrasting with prose kill criteria, so an agent can tell it apart from compute_dealbreakers_v2 and similar compute tools.

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: use this after validate_unit_economics and compute_dealbreakers_v2 have produced outputs, and when an ICP drift count is available. It also says it 'replaces prose kill criteria', which is an implied when-not. It does not explicitly name alternatives or list exclusion conditions, but the input-dependency guidance is strong enough for an agent to infer appropriate usage.

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