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

Annotations cover the safety profile (readOnly=false, idempotent=false, destructive=false), and the description adds real behavioral context beyond them: firing on the next matching observation, count-limited or until removed, and every firing emitting a fault.injected timeline event. It omits auth requirements and the exact interaction with persistent/run-end lifecycle, keeping it below 5. No contradiction with destructiveHint=false.

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?

Two dense sentences, front-loaded with the core action and followed by the when-to-use rationale. The long enumerated middle clause is information-rich but borders on run-on, slightly hurting scannability.

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 12-parameter mutation tool with no output schema and rich schema documentation, the description covers the fault-type taxonomy, firing/lifecycle semantics, and event emission. It leaves resource-compatibility rules and count/persistent interplay to the schema, which is acceptable given the high coverage.

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 83%, above the 80% threshold, so baseline is 3; the description goes further by mapping the 'type' enum values to their observable effects (delay/duplicate/drop/reorder/payload mutation vs. status override, connection reset, bandwidth throttle, partial cut-off). It does not spell out per-parameter constraints already present in the schema, so 4 is fair.

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?

States a specific verb and resource (arm deterministic interference on one resource of an active run) and enumerates the concrete fault families, so an agent can immediately distinguish it from rig.fault.remove. The title 'Arm a fault' and description align.

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?

'Use to prove the application survives duplicates, delays, reordering, corrupted payloads and dependency failures' gives a clear purpose-driven context for when to reach for it. It does not, however, explicitly name the alternative sibling (rig.fault.remove) or state exclusions, so it falls short of a 5.

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