codex_research

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

With no annotations provided, the description carries the full burden. It reveals the multi-turn process and time trade-off, which are behavioral traits. However, it does not address permissions, side effects, or rate limits. The information is adequate but leaves gaps for mutation or state-management details.

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 exceptionally concise: two sentences that front-load the core purpose, then explain the process and trade-offs. Every sentence adds value with no redundancy or filler.

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 complexity (9 parameters, no output schema), the description explains the purpose and process but lacks details about return values, error handling, or how the session_id and working_dir interact. It also does not explicitly guide comparison with siblings beyond the speed-depth trade-off. It is functional but not fully 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 description coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema; the parameter descriptions in the schema are already detailed (e.g., max_turns explains each turn deepens investigation). The tool-level description does not enhance parameter understanding.

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 tool does 'deep-dive research via GPT Codex' with a multi-turn process that surveys, drills, and synthesizes. It differentiates from siblings like codex_ask and codex_debug by emphasizing depth over speed and listing specific use cases (architecture exploration, library evaluation, understanding codebases).

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?

While it explicitly lists use cases ('Use for architecture exploration, library evaluation, or understanding unfamiliar codebases'), it implies when not to use with 'Can take minutes — trades speed for depth,' but does not name specific alternative tools. The context is clear, but more direct exclusions would strengthen it.

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