memory_episode_end

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

With no annotations, the description carries the burden. It discloses the state transition (closing and popping to session), the return value, and the empty-open edge case. However, it does not mention whether the close is destructive/reversible, any side effects on child data, or permission requirements, leaving some behavioral ambiguity.

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 sentences, no filler. The description is front-loaded with the action and immediately states the result and edge case, making it highly scannable.

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 zero-parameter tool with straightforward behavior, the description fully covers the action, result, and empty case. The output schema exists and the description already explains the return value, so no additional context is needed.

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?

The tool has zero parameters, so the baseline is 4. The description does not need to add parameter-level detail; it correctly focuses on behavior and return value.

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 ('Close') and resource ('current open episode'), and clearly differentiates from sibling tools like memory_episode_start and memory_episode_summary by stating it ends an episode and pops to its parent. The scope is unambiguous.

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 'current open episode' implies the tool should be used only when an episode is active, and the note about returning {} when nothing is open clarifies the no-op case. However, it does not explicitly state when to use this instead of other memory tools, nor provide alternatives or preconditions.

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