Initialize Session

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

Annotations already indicate this is a mutating, non-idempotent operation. The description adds valuable behavioral context beyond annotations: the session is durable, reviewer models are not invoked yet, and evidence submitted later is persisted automatically without human intervention or an attach step. This meaningfully clarifies side effects and workflow behavior.

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 with no filler. The core purpose is front-loaded, and the second sentence adds essential workflow context about evidence persistence and the absence of reviewer invocation. Every sentence earns its place.

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?

The description covers the key workflow context: when to call it, what it does not do, and how evidence should be handled afterward. It does not name the specific 'subsequent review starter' tool or describe return values, but given the moderate complexity and the presence of sibling tools, this is a minor gap rather than a critical omission.

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 only 50%, and the description does not compensate for the undocumented caller and response_format parameters. It mentions the evidence field, but that is not a parameter of this tool. The description adds no meaning to task, caller, review_focus, or response_format beyond what the schema already provides.

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 states a specific verb and resource: 'Create a durable cross-review session'. It also distinguishes itself from siblings by noting it runs 'after probing provider availability and model selection' and explicitly says 'This does not call reviewer models yet', separating it from ask_peers and session_start_round.

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 gives explicit sequencing guidance ('after probing provider availability and model selection'), clarifies what the tool does not do ('does not call reviewer models yet'), and tells callers to submit evidence via the subsequent review starter instead of using session_attach_evidence. This effectively provides when, when-not, and an alternative.

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