start_project_mission_run

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

Annotations only signal not read-only, not idempotent, not destructive, and open-world. The description adds meaningful behavioral disclosure: it records a save point, requires confirm_start, and does not dispatch agents, invoke tools, authorize live actions, write to external systems, or claim mission completion. This gives the agent a much richer side-effect profile than the structured annotations alone.

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: the core purpose appears in the first sentence, and the second paragraph adds necessary precondition and non-effect details. Every sentence earns its place, with no filler or repetition.

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?

An output schema exists, so return-value documentation is not required from the description. The description is complete enough for the checkpoint/save-point semantics, including preconditions and non-actions, and only a few optional parameter meanings are left vague.

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 0%, so the description must compensate. It explains the critical confirm_start flag, including when it is appropriate to set it, and references the context references, play style, and shadow skill loadout concepts that map to context_source_refs_json, play_style_id, and selected_skill_ids_json. A few optional params such as run_id, note, skill_trial_arm, and exact JSON shapes remain under-specified, but the most safety-relevant parameter is well covered.

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 ('lock') and resource ('current mission briefing') and clarifies that this is a save-point/checkpoint operation rather than an execution launcher. The explicit negative list ('does not dispatch an agent, invoke a tool, authorize a live action...') differentiates it from many mission execution and action-oriented siblings.

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 clear sequencing guidance: use this before any separate action, and only set confirm_start=true after checking the campaign, context references, play style, and shadow skill loadout. It does not name an alternative sibling explicitly, but the 'before any separate action' instruction and the boundary of what it does not do provide sufficient usage context.

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