start_investigation

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

No annotations are provided, so the description carries the full burden of disclosure. It does disclose important side effects: reuse without re-query, flagging, candidate return, and the 'never merged silently' guarantee. However, it does not disclose potential costs (e.g., whether this launches long-running queries, whether it has side effects beyond a read, or what the compaction/linking entails). For a tool that starts work on production systems, more disclosure would help.

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 a single dense paragraph plus a code example. It is reasonably concise and front-loads the core purpose and key reuse behavior early. The inclusion of an inline example for `symptom_signature` is valuable. It could be trimmed slightly, but the content density is good and every sentence earns its place.

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 10 parameters with 0% schema coverage and no output schema or annotations, the description does substantial work but leaves gaps. It explains the reuse/merge semantics and the signature format, but does not clarify what each parameter controls (especially start/end/window_minutes interplay, environment scope, symptom_kind options). For a tool managing production investigations, the agent needs more parameter grounding to invoke correctly, though the core question/services/signature trio is well handled.

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 compensate. It does explain `symptom_signature` with a concrete example format ('HTTP_502:checkout'), and implies the meaning of several parameters like `force_new`, `window_minutes`, `environment`, `consumer`, and `services` through context. However, several parameters (start, end, symptom_kind, consumer) are only hinted at or left implicit, meaning a single broad sentence carries much of the burden across 10 parameters.

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 verb ('Begin or reuse') and the resource ('bounded production investigation'). It specifies the primary output (a 'compact, source-linked evidence capsule') and distinguishes itself from siblings by describing its unique behavior around reusing existing investigations and handling related-but-not-identical matches. This is specific and non-tautological.

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 gives explicit guidance on when reuse happens: identical investigations are reused and flagged, while related-but-not-identical candidates are returned for the agent to choose ('never merged silently'). It also explains the `force_new` semantic implication by contrasting against reuse behavior, indicating when a new investigation would be forced. This is strong behavioral guidance for a tool that could otherwise silently behave unexpectedly.

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