memory_causal

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

No annotations are provided, so the description carries the behavioral burden. It communicates a read/compute behavior by saying it returns a before/after mean change, but it does not explicitly state that the operation is non-destructive, how the before/after boundary is determined, or whether any special permissions or data requirements apply.

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 a single sentence that front-loads the core concept and result. It contains no filler, repeats no parameter names unnecessarily, and is easy for an agent to parse quickly.

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 four parameters, no output schema, and no annotations, a single-sentence description is thin. The agent is not told the shape of the returned value, how to interpret 'mean change,' how the causal calculation is scoped, or when to prefer this over sibling tools. This leaves important operational and selection context 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 only 25% because only `window` has a description. The prose partially compensates by explaining `verb` as an action and `entity.metric` as a metric, but it does not describe valid values or the relationship between `window` and the before/after computation. Thus it adds some meaning beyond the bare schema but does not fully compensate for the low coverage.

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 states a specific analytical purpose: measuring the causal impact of an action (verb) on a metric (entity.metric) and returning the mean change before vs. after the action. This clearly differentiates the tool from siblings like memory_trend and memory_anomaly by emphasizing causality and before/after comparison.

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 description implies when to use the tool: when the caller wants the causal effect of an action on a metric. However, it does not explicitly list alternatives, exclusion criteria, or prerequisites such as needing pre-existing action history, so the agent must infer usage context from the tool name and siblings.

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