scan_repo

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

With no annotations, the description must disclose side effects, permissions, and return behavior. It describes a scan operation (likely read-only) but does not explicitly state that it is non-destructive, whether it produces a report, or if it has any side effects. The 'full deployment' requirement is useful but insufficient for full transparency.

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, front-loads the action, and contains no fluff. Every word adds value, efficiently conveying purpose and a key requirement.

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?

The tool has no output schema and no annotations, so the description must explain return values and behavioral context. It does not describe what the scan returns, how results are formatted, or any success/failure indicators. Given the complexity of a multi-file scan, this is a significant gap.

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 schema already covers the single 'path' parameter with 100% coverage. The description adds a meaningful constraint: the path must reference a full deployment on the TASIE backend, which goes beyond the schema's basic 'directory path' definition.

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 states the action (ingest), the resource (multi-file repository on TASIE host), and the specific outcomes (discover routes, scan modules for vulnerabilities). This distinguishes it from sibling tools like scan_code (likely per-file) and scan_dependencies.

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 provides a prerequisite (path must exist on TASIE backend full deployment) but does not explicitly state when to use this tool over alternatives like scan_code or detect_frameworks. The phrase 'multi-file repository' implies it is for whole repos, but no explicit comparison is made.

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