deep_explore

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

No annotations are provided, so the description carries the full burden. It discloses the tool runs in a READ-ONLY sandbox with capped scope and returns findings only, plus the cost factor. This covers safety and cost, though it doesn't describe what happens on failure or how findings are structured, which would be useful but not essential given the read-only nature.

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, front-loaded with purpose and alternatives. Every sentence earns its place, covering purpose, behavior, cost, and fallback directive with zero waste.

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?

While there is no output schema, the description says 'returns findings only' – vague but acceptable given the tool's nature as a fallback for open-ended investigation. It leaves some ambiguity about the exact output format, but the tool's purpose is inherently open-ended. Considering the complexity and the rich parameter documentation, this is reasonably complete.

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 coverage is 100%, so baseline is 3. The parameter descriptions add significant value beyond schema: path is clarified as scope restriction, model includes explicit user-confirmation requirement and cost warning, project must be named by user and passed explicitly, session_token required and re-armed per chat. These are practical usage hints that greatly help the agent invoke correctly.

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?

Description states precisely that this is a fallback for questions the free bridge tools can't answer, with a concrete example ('trace how auth is wired across 30 files'). It clearly identifies the tool as the heavyweight investigation option, distinct from simpler siblings like list_tree/read_file/grep.

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?

Explicitly instructs to try list_tree/read_file/grep/git_* first before using this tool, and notes the cost implication ('Costs Codex usage'). This gives the agent a clear decision rule for when to use it vs alternatives.

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