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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds genuine behavioral context: it computes both cascades, decomposes the gap into leverage, velocity, SNR, and scale contributions, and returns the most explanatory factor. No contradiction with annotations.

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 two sentences, front-loads the core question, and avoids filler. It is somewhat jargon-heavy, but every sentence contributes purpose, behavior, or input semantics.

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?

Despite the strong purpose framing, the tool has 10 parameters, no output schema, and low schema coverage. The description leaves the agent without enough detail about required parameter groups, how codenames map to pillar data, or the exact structure of the returned decomposition beyond 'most explanatory factor.'

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 only 20%, with only a_codename and b_codename documented. The description mentions 'two sets of pillars' but does not enumerate the a_input, b_input, a_output, b_output, cache_read, or cache_write parameters, nor does it clarify which combinations are required or how codename input relates to pillar input. This is a significant gap for a 10-parameter tool.

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 answers a very specific question: what separates operator A from operator B, and it promises decomposition into primary cause, secondary cause, and offsetting weakness. This clearly distinguishes it from simple comparisons and from siblings like compare_to_field or who_operates_like_me.

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 intended use is explicit: use when you need to know what specifically separates two operators, not merely which one has more yield. It also states the two accepted input modes: codenames or two sets of pillars. It does not explicitly name alternatives or exclusion conditions, so it stops short of 5.

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