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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description's language of 'configuring' and 'injecting' policies reads like state mutation, and idempotentHint=false hints at repeated-call effects; the description never resolves whether a policy persists, applies only to the simulation run, or can be removed. It adds useful detail on the specific error modes injected, which annotations do not convey. No outright contradiction, but the persistence/side-effect question an agent would ask is left open.

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 dense sentence that front-loads the verb and resource, followed by a compact parenthetical of supported modes. Efficient with no filler, though the long parenthetical list strains readability slightly.

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?

An output schema exists, so return values need not be explained, and all three parameters are documented in the schema. However, for a tool that stands up fault policies inside simulations, the description omits scope duration, whether policies are removable, and how they interact with concurrently running simulations, which is a real gap for correct invocation.

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 100% and the enum already lists the fault types, so the description's main added value is tying those labels to concrete HTTP semantics (429 rate limits, 500 errors, timeouts, 401 unauthorized, malformed JSON). It does add marginal meaning, but never comments on targetToolName accepting 'all_tools' or on how failureProbability behaves per invocation.

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 concrete verb ('Configures') and object ('dynamic chaos injection policies') and enumerates the supported fault modes, so the agent knows exactly what capability this exposes. It stops short of differentiating itself from nearby siblings such as systemores_stress_test_agent or systemores_audit_tool_integrity, leaving boundary judgment to the tool name.

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 phrase 'during simulations' implies the operating context, so usage is inferable but never stated as an explicit condition. There is no 'use this instead of X when Y' routing and no guidance on when fault injection is inappropriate.

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