Begin session

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description goes further by listing what the call returns (mode, plan, budget, deny_tools, host_script, skill_ref) — genuinely additive since there is no output schema — and names the internal machinery (plan compiler + budget guard). It still does not say what state the session creates or how long it persists.

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?

Dense and front-loaded: the action and its two subsystems come first, inputs next, outputs third, and the ordering imperative last. It is telegraphic rather than wasteful, though the 'Session Protocol v1.2' version tag carries little decision value for an agent.

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 no-required-parameter bootstrap tool in a large sibling cluster with no output schema, the description does supply return fields and call ordering. But five of eight inputs remain unexplained and there is no guidance on defaults or on the session lifecycle it initiates, leaving the definition minimally adequate rather than complete.

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 13% across 8 parameters, so the description must compensate, and it largely does not: 'goal (≤500)' and 'host_budget tiny|small|normal' merely restate constraints already in the schema, while project_root, test_commands, correlation_id, max_tool_calls, and expected_artifacts are undocumented in both places. It does not explain the semantics of the intent enum or how max_tool_calls interacts with the budget guard.

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?

States a specific verb+resource: 'begin session with plan compiler + budget guard', and 'Call first' positions it as the entry point in the session lifecycle alongside tick/next/end siblings. It does not distinguish itself from other starters like grok_agent_start or grok_delegate_start, so it is clear but not fully sibling-differentiated.

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 first' gives explicit ordering guidance, which is the key usage signal for a session bootstrap tool. However, there is no statement of when not to use it, no prerequisites, and no routing to alternatives such as grok_agent_start or grok_delegate_start.

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