flow.clear_memory

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

With no annotations provided, the description carries the full behavioral burden and includes useful inline tags: [approval required], [workspace write], and [risk:dangerous]. It also explicitly discloses that source code is untouched. It stops short of describing irreversibility or what specifically is deleted from flow memory, but the core side effects are surfaced.

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 short sentences plus compact risk tags. It front-loads the action and safety classification and every sentence adds information without 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?

For a dangerous, approval-required destructive tool with no output schema, the description is incomplete. It omits when this tool should be used, what clearing memory entails for active flows/checkpoints, and how the confirm parameter should be satisfied. The risk tag and artifactsDir scope are useful but do not make the definition callable without further inference.

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 0% and the description never explains the required confirm parameter. An agent cannot tell from the description what value confirm should hold, how it relates to the approval requirement, or any required confirmation string. The tool description adds no parameter-level meaning beyond the bare name 'confirm'.

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 uses a specific verb and resource: 'Clear flow memory under artifactsDir.' It clearly states what is affected and adds an important scoping statement that app source code is not modified. However, it does not explicitly differentiate from flow.read_memory or related flow lifecycle tools beyond the verb itself.

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 call clear_memory versus alternatives like flow.read_memory or flow.record_checkpoint. The 'does not modify app source code' note is a safety clarification, not a usage condition, so an agent is left to infer when this destructive reset is appropriate.

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