memory_episode_start

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

With no annotations provided, the description carries the full burden. It discloses that the tool opens a sub-episode, nests under the session episode, and that memories stored while open carry its id + title, enabling scoped search. It also notes that memory_episode_end pops back to the session. This is meaningful behavioral context, though it doesn't cover potential errors or idempotency.

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 concise and well-structured: a clear opening statement, a sentence explaining nesting and memory effects, a pointer to the closing tool, and a return format line. Every sentence contributes essential 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?

Given that the tool has only two parameters and no annotations, the description covers the core behavior, nesting, memory association, closing mechanism, and return shape. It omits the purpose of the 'hint' parameter, but with an output schema present, the lacking explanation of hint is a minor gap for such a simple tool.

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%, so the description must compensate for parameter meaning. It implies that 'title' is used as the episode name ('named sub-episode'), but it does not explain the 'hint' parameter at all. The description adds minimal value beyond the schema's existence of parameters.

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 clearly states the tool's action: 'Open a named sub-episode for a substantial multi-step task.' It identifies the resource (sub-episode) and its nesting behavior, and distinguishes it from sibling tools like memory_episode_end by explicitly referencing that tool for closing.

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 specifies when to use the tool ('for a substantial multi-step task') and clarifies how it fits into the episode lifecycle ('nests under the auto-managed session episode'). It also mentions memory_episode_end as the counterpart, providing context but not explicit exclusions or alternative tools.

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