start_team

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

The description itself transparently discloses the workflow (queued start, parallel workers, correction rounds, awaiting review), but the annotations declare readOnlyHint=true while the description describes a stateful operation that queues work and spawns agents. This is a direct contradiction with the annotations, which per the rubric forces a score of 1 and an Annotation Contradiction flag.

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 two sentences and roughly 30 words, with the core action front-loaded and the workflow detail providing real information about execution behavior. There is no filler or repetition, though the prose is slightly flowery.

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 14-parameter tool with no output schema and no parameter documentation, the description omits critical operational facts: what the call returns (team ID? run ID?), how to monitor or manage the running team (siblings get_team, team_dashboard, message_agent, cancel_team indicate an async lifecycle), and what 'queued' means for the caller. The workflow prose helps but does not close the gaps needed for correct invocation and follow-up.

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% across 14 parameters, so the description must compensate heavily, but it explains no parameter directly. It supplies workflow vocabulary (coordinator, review rounds, queued, agents) that hints at coordinator_model, review_rounds, and agents, yet leaves cwd, objective, effort, model_policy, max_retries, timeout_minutes, acceptance_criteria, context, and name semantically opaque.

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 opens with a specific verb+resource ('Start a queued multi-agent Antigravity team') and elaborates the workflow (parallel investigation, lead coordinator report exchange, correction rounds, independent Codex review). This clearly identifies what the tool does and differentiates it from single-agent siblings like start_analysis or start_review, though it never names those alternatives explicitly.

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 no explicit statement of when to use this tool versus start_analysis, start_review, resume_team, or the other team-management siblings, and no exclusions or prerequisites. However, the workflow detail ('Workers investigate in parallel... correction rounds... Codex review') implies the tool is for heavyweight multi-agent investigation, giving the agent a weak but real usage signal.

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