Launch agent

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

With annotations already declaring this is a non-read-only, open-world, non-destructive operation, the description adds real value beyond them: required permissions, atomic commit of config/agent/initial input, and detailed idempotency-key replay semantics ('the retry body is not applied and integration references are not resolved again'). It stops short of 5 because it does not say what the response looks like or what happens on permission failure.

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?

Four compact sentences, front-loaded with the action and followed by prerequisites and replay behavior; every sentence carries information. The permission sentence is dense but not wasteful.

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 an 11-parameter tool with deeply nested objects and no output schema, the description covers the main behavioral risks (atomicity, permissions, replay) but omits how the three launch sources (profile / config / config_source) relate, what the returned agent contains, and error/conflict behavior.

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 coverage is 64%, so the schema already documents much of the surface, and the description adds meaning for tools, subscriptions, interaction handlers, and the attributed initial text input. It says nothing about name, profile, orgID, projectID, or config_source, so it only partially compensates for the uncovered parameters.

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 ('Launch from a pinned config') and enumerates what can be attached in the same call, so an agent can distinguish this from configs_create, profiles_create, or agents_update. It never explicitly names a sibling, and the phrase 'pinned config' is slightly ambiguous given the schema also accepts profile and config_source, so it falls short of a 5.

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?

It gives the conditions required to succeed (project management permission for integration capabilities, agent operate permission for launching an existing config) and describes idempotency-key replay, which is useful context. However, there is no explicit 'use this when / use X instead' routing against the many sibling tools (agents_input, configs_create, profiles_create), so usage is only implied.

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