generate_report

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

Annotations provide idempotentHint=true, readOnlyHint=false, and destructiveHint=false, so the agent already knows it writes but is safe to call repeatedly. The description adds useful context beyond those: it states the default output location (<project>/.shipsafe/) and that it is automatically git-ignored, plus describes the HTML report's interactive features. It does not describe error cases (e.g., missing scan) but does not contradict annotations.

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 compact and well-structured: purpose sentence, a bullet on HTML report features, a note on default location, then a concise 'Args' list. It is front-loaded with the primary action, and every sentence adds value. No fluff or redundancy.

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 report generation tool, the description covers the core behavior (what it writes, where it writes, available formats) and the output schema exists to describe the return value. It does not explicitly mention prerequisites (e.g., that a scan must have been run) but the phrase 'for the latest scan' plus the sibling scan_project makes that inference reasonable. Missing details like error handling are minor given the output schema and the tool's straightforward nature.

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%, so the description must carry the full parameter explanation. It does: it explains each argument ('format' with enumerated values and their meaning, 'path' as project root with a default, 'output' as an explicit file path). This adds meaning far beyond the bare schema types and defaults, fully compensating for the lack of schema descriptions.

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 clear verb+resource: 'Write a shareable report for the latest scan.' It specifies the output artifact and its key features (score ring, severity filters, copy-fix button), and the sibling context (scan_project, list_findings, etc.) shows this tool is distinct because it generates a report rather than performing analysis. The purpose is unambiguous and not a tautology.

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 implies it should be used after a scan by saying 'for the latest scan,' but it does not explicitly state when to use it versus alternatives, nor does it list any exclusions (e.g., 'use list_findings for raw findings'). It does explain the format options and defaults, which helps the agent decide, but lacks explicit routing or when-not-to-use guidance.

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