Launch a project

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

Annotations already flag destructiveHint/readOnly=false/openWorld, but the description adds genuinely new behavior: it consumes a launch credit, sbm_test_ keys produce a test launch, and live keys trigger a confirmation question to the client's own user. That last point is non-obvious third-party side-effect disclosure. It still doesn't say whether a launch is reversible or what a failed launch does to the credit.

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?

Three sentences, front-loaded with what the tool does, followed by the precondition and the live-key caveat. Dense but every clause carries information. The opening clause 'spends one launch of the agency' is slightly convoluted but still earns its place by conveying quota consumption.

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 destructive mutation with rich annotations, full schema coverage and no output schema, the description covers the essential unknowns: quota spend, test vs live key behavior, and the mandatory preview/confirm loop. Nothing an agent needs in order to invoke it safely is missing.

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 100%, so every parameter including confirm_selected, directories, auto_replace and excluded_directories is already documented in the schema. The description's 'confirm_selected is the count they agreed to' essentially restates the schema's own wording. Baseline 3 for a fully documented schema with no material added semantics.

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 action (start submissions / spend one launch credit on a project) and ties it to the concrete resource. The 'agency' and 'one launch' phrasing is domain jargon, but the pairing with preview_launch and sbm_test_ keys makes the intent recoverable. It clearly is not a read tool like get_project or preview_launch.

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?

Gives an explicit prerequisite workflow: call preview_launch with the same arguments, get user agreement, then pass that agreed count as confirm_selected. That routes the agent away from blind launching. It does not state explicit when-not-to-use conditions (e.g. insufficient credits, draft state), so it stops short of 5.

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