scan_repo

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

Without annotations, the description covers the tool's behavior: it scans, returns readiness score and findings list, and lists checked categories. It does not mention potential side effects or limitations like rate limits, but the described behavior is complete for a read-only scan tool.

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?

Two sentences convey purpose, outputs, usage guidance, and constraint. No redundant information; every sentence adds value.

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?

Given the single parameter, no output schema (output described in text), and related sibling tools, the description fully covers what the tool does, its prerequisites, and its output, providing complete contextual information.

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?

The single parameter (repoUrl) is described in the schema (100% coverage), and the tool description adds extra context on format (github.com/<owner>/<repo>) and example URL, enhancing understanding beyond the schema.

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 clearly identifies the tool as running a CheckMyLaunch readiness scan on a public GitHub repository, listing specific findings (secrets, risks, deployment problems) and outputs (score and findings list). It distinguishes from siblings (scan_url for generic URLs, get_repair_prompt for repair prompts) by specifying the GitHub repo context.

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 explicitly advises when to use ('after making changes to check safe to ship') and when not ('private repos need signed-in flow'), providing clear usage context and an alternative for private repos.

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