Initialize Session

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

Annotations only provide flags (readOnlyHint false, openWorldHint true, idempotentHint false, destructiveHint false), so the description carries the burden of behavioral disclosure. It adds meaningful context: the session is durable, the tool does not invoke reviewer models, and the runtime persists evidence automatically. This goes beyond the annotations, though it does not cover duplicate-call behavior or return details.

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 compact and front-loaded with the core purpose in the first sentence. The remaining two sentences add behavioral and workflow context without excessive fluff. The third sentence is slightly tangential to the tool itself but still earns its place by preventing misuse of session_attach_evidence.

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?

There is no output schema, and the description does not state what the tool returns (e.g., a session ID needed by session_read, session_poll, or session_start_round). It also leaves the relationship to 'probing provider availability and model selection' ambiguous. For an initialization tool that subsequent siblings depend on, this is a significant completeness gap.

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 50%; task and review_focus have descriptions, while caller and response_format are only represented by enums/defaults. The description does not elaborate on any current parameters, only mentions the evidence field of a subsequent step. The parameters are reasonably inferable from the schema, so this is adequate but not enhanced by the description.

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 adds useful scope by noting it does not call reviewer models yet, which distinguishes it from round-starting siblings like session_start_round. However, it does not explicitly name sibling alternatives, so it falls short of full differentiation.

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 implied sequencing: 'after probing provider availability and model selection' and a workflow note about submitting evidence without session_attach_evidence. But the description never explicitly says when to choose this tool over session_preflight_check, session_start_round, or session_start_unanimous. Usage context is present but not explicit.

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