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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it only reveals that a session_id is returned. It does not disclose that each call creates a new session (non-idempotent), that TTL governs expiry, that unclosed sessions may hold resources, or that callers should pair this with memory_session_close. The existence of a TTL parameter and a close sibling implies real lifecycle behavior that the description leaves unstated.

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?

A single front-loaded sentence with zero filler; verb, resource, and output all appear immediately. It earns its place. It borders on under-specification, which is penalized elsewhere, but as pure conciseness it is well-formed.

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 the output schema exists and all five optional parameters are fully documented, parameter understanding is complete. The gap is contextual: nothing explains the session lifecycle (open → work → close), when to prefer ensure over open, or what side effects opening creates. For a session-management tool in a large memory* family, this missing lifecycle context is a real but not fatal shortfall.

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%, and the schema descriptions are rich (e.g., repo and github parameters explain tag inheritance for distilled memories), so the baseline of 3 applies. The description adds nothing about parameters, but it does not need to — the schema already carries the semantic weight.

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 ('Open'), names a clear resource ('working-memory session'), and states the primary output ('return a session_id'). This distinguishes it from the session lifecycle siblings at a glance — append, close, get are all different verbs. However, it does not differentiate from memory_session_ensure, which plausibly also opens a session when none exists, leaving some ambiguity between the two.

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 use this tool versus the closely related siblings. Critically, memory_session_ensure is a likely get-or-create alternative to memory_session_open, and memory_session_close implies a lifecycle responsibility — yet the description mentions none of these. The agent must infer usage from the schema alone.

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