create_session

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It does disclose privacy-relevant behavior: attestation happens server-side inside Haven, and the raw session token is never exposed. It also indicates that shareLocation is an opt-in affecting required parameters. However, it does not mention whether the session is persistent, expires, can be reused, or what error may occur if called twice. Given zero annotations, a 3 is fair for partial disclosure but leaves durability questions open.

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?

Three sentences with a clear front-loaded purpose, a security behavior, and a sequencing rule. The first sentence is informative, the second adds behavioral value, and the last is a compact usage directive. Slight redundancy with the schema's shareLocation description exists, but the description stays compact for an 8-parameter tool.

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 session-opening tool with no output schema and no annotations, the description sufficiently establishes what it does, why it is called first, and how the session token is handled. It does not specify session lifetime or idempotency, and it doesn't describe what a successful call returns (likely just 'ready'), which are minor gaps for an agent deciding whether to call this tool versus session_status or leave.

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 schema covers 100% of parameter meanings, so the baseline is 3. The description goes beyond the schema by explaining the scoped-session behavior and the relationship between shareLocation and the location fields, but it does not add new parameter-level meaning beyond what the schema already provides. It correctly echoes that omitting location fields still works for Looking/Handoff/Garden.

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 names a specific verb ('Open'), a specific resource ('scoped Haven Gateway session for this connector'), and explains how this session differs from typical ones: attestation is handled inside Haven, and the adapter never returns credentials or the raw session token. It also tells the agent which operations follow, which clearly distinguishes it from the sibling tools listed.

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?

'Call this before other Haven tools' is an explicit sequencing instruction that tells both when to use it and that it is a prerequisite for its siblings. The description also states what the adapter does with the session token, eliminating guesses about whether the session token should be returned or persisted by the agent.

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