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

Goes well beyond the lone readOnlyHint=false annotation: it discloses exactly what is destroyed (dialogue turn state), what survives (persistent memory, learned facts, document registers), and that X-License-Key authentication is required. This is the mutation profile an agent needs before calling.

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?

Front-loaded with the core action and the key preservation guarantee, which is efficient. It does restate the preservation point three times ('strictly preserving', 'persistent memory is preserved by design', 'leaves long-term memory intact'), a small amount of redundancy.

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?

With an output schema present, return values need not be described, and the description covers mutation scope, exclusions, and auth. The only gap is that the optional space_id scoping/default is left entirely to the schema, but nothing critical for correct invocation is missing.

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 100%, so the space_id parameter including its default behavior is already documented. The description never mentions space_id or partitioning, adding no semantics beyond the schema; baseline 3 applies.

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: clears conversational dialogue turn history for a session while preserving persistent memory. This is clearly differentiable from siblings like icx_purge_source and icx_remember, which operate on stored knowledge rather than ephemeral turn state.

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?

Explicitly names the triggering situation (switching topics, clearing context between independent tasks) and an explicit exclusion (do NOT use for wiping persistent memory). An agent can decide between this and the memory-mutating siblings without further inference.

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