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

Annotations already declare this is not read-only, not idempotent, and non-destructive; the description adds genuine context beyond that by disclosing the returned `session_id` and its mandatory downstream role, plus that server instructions arrive at initialization. It omits session lifetime, whether multiple sessions may coexist, and any authorization requirements.

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 short sentences, front-loaded with the action and followed by the contract the caller must honor. Every clause carries operational weight, including the note about server instructions.

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 an output schema present, the return value needn't be fully explained, and the description still flags `session_id` as the critical output. Complete enough to invoke correctly, with only minor gaps around session reuse and lifecycle for a zero-parameter bootstrap 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate beyond the empty schema. Baseline 4 applies: no parameter-level gaps exist to compensate for.

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 and resource ('Create a new Compass session') and states the key artifact returned, a `session_id`. It implicitly separates itself from siblings by declaring that the id is required by every subsequent Compass call, though it never explicitly contrasts with entry points like `design_start_for_order`.

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?

'MUST be passed into every subsequent Compass tool call' establishes this as the bootstrap step that precedes all other calls, which is clear usage context. It stops short of explicit alternatives or exclusions — nothing says whether an existing session can be reused or when re-invocation is appropriate.

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