chaos-score

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

With no annotations, the description carries the full burden; it does disclose the bounded [0, 100] output and that the result is a pure function of four supplied readings, which implies a side-effect-free computation. It does not state that the tool is read-only/no-side-effect explicitly, nor that asset_class switches which interpretation the readings take — a material behavioral fact that lives only in the schema text.

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?

One tight sentence with the output range and input source front-loaded and zero filler. It is arguably undersized for a five-parameter tool with dual asset-class semantics, but nothing in it is wasted.

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 five required parameters, no output schema, no annotations, and 20% schema coverage, the description omits too much: required asset_class, the equity re-specification of two field names, and any hint of the return shape beyond the [0, 100] range. The nested schema prose covers some of this, but the description itself does not leave an agent fully equipped to call it correctly.

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% (asset_class alone is described at the property level), so the description needed to compensate and does not: it says 'four supplied readings' without naming them, giving units, or flagging that stablecoin_deviation and sequencer_delay are reinterpreted for equities. The rich unit discussion sits in the nested $defs text, not in the tool description, so an agent skimming the description gets no parameter meaning.

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 names a specific resource (a composite market-stress index) and states its output range [0, 100] and that it derives from four supplied readings, so an agent knows exactly what it computes. It does not differentiate itself from stress-adjacent siblings such as lending-stress, peg-deviation, or sequencer-latency, which is the only thing keeping it below a 5.

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 guidance on when to reach for chaos-score versus the many single-signal siblings (lending-stress, peg-deviation, ofi, gas-vol), nor any note that it aggregates those readings into one number. The agent must infer its role as a composite from the one-line description alone.

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