investigate

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. The description adds that the tool returns a compact JSON bundle and replaces chained calls, but does not elaborate on behavior beyond what is implied (e.g., no mention of rate limits, data size constraints, or error conditions). The description adds some context but does not substantially extend beyond 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 concise: two sentences that front-load the primary purpose and default behavior, followed by the recipe options and output format. No redundant or extraneous 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 tool's complexity (6 parameters, no output schema, many siblings), the description is fairly complete. It covers default operation, recipe choices, and the fact it replaces chained calls. However, it lacks explicit details about the return structure (e.g., fields in the JSON bundle) and does not mention any prerequisites or error scenarios. With no output schema, more detail on the output would improve completeness.

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?

Input schema covers 100% of parameters with descriptions. The description adds value by explaining the 'recipe' parameter: listing the audit options (architecture, dead_code, security, perf) and their aliases, and clarifying that 'target' can skip query. It also mentions the default format ('toon') and that recipe provides specialized audits, adding context 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 'investigate' as a fused investigation tool that combines query, context, impact, and test_impact by default, and can use specialized audit recipes like architecture, dead_code, security, and perf. It states it replaces chained MCP calls, distinguishing it from sibling tools that perform individual tasks. However, it does not explicitly mention the target resource (codebase) or use a strong verb-resource pair, slightly reducing clarity.

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 guidance on when to use the tool: by default for combined analysis, or with a recipe for specialized audits. It notes it replaces chained MCP calls, implying consolidation of multiple tool calls. However, it lacks explicit when-not-to-use guidance or direct comparisons to siblings like 'query', 'dead_code', or 'hotspots', which could help an agent select the appropriate tool.

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