ask_codex

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

No annotations are provided, so the description carries full burden. It discloses hermetic and read-only operation ('can't see or touch your repo'), single-turn behavior, the binary_missing error condition, and refusal boundaries for offensive-security and non-software domains. This is exemplary transparency for a tool with zero 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 long but front-loaded with the core purpose and every sentence adds functional or routing information. It loses a point due to slight redundancy: `ask_council` appears twice in the alternatives list, and the final enumeration of siblings is lengthy relative to what the sibling list already provides.

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 complex tool with no output schema and no annotations, the description covers purpose, prerequisites, error mode, behavioral limits, scope restrictions, and context usage. Nothing an agent needs to decide whether to call this tool or how to pass the required parameters is missing. The only absence is an explicit return format, but for an ask-style tool that is sufficiently implied.

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 usage meaning beyond the schema by explaining the `context` parameter's purpose ('put the code it needs in `context`') and clarifying what kinds of `question` are acceptable ('Broad and conceptual engineering questions... are fine'). It doesn't redundantly repeat schema text, and `context_ref` is already well documented in 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 states a specific verb and resource: 'Ask OpenAI's model (GPT-5.6 Sol, via the local codex CLI...)' and enumerates the scope: reasoning about code structure, data/control flow, architecture, and design trade-offs. It distinguishes itself from siblings by explicitly naming alternates at the end, so an agent can tell it apart.

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 when-to-use guidance: 'add a snippet or file path in `context` when the question is about existing code' and routes to alternatives: 'Use `ask` for Fable's built-in ChatGPT, `ask_chain`/`ask_debate` for multi-step reasoning, `ask_council` for broader advisor groups...' It also states prerequisites: 'Requires the `codex` CLI installed and logged in on the server.'

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