codex_consult

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

No annotations are provided, so the description carries the full burden, and it discloses almost nothing behavioral: no cost/latency expectations, no mention that the top-tier 'astra' model requires a mandatory user_confirmed flag, and no statement about what the call returns. For a tool that proxies an external model with tiered, gated options, this is a significant transparency gap.

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?

A single front-loaded sentence with zero filler; the verb and the evaluative scope land immediately.

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?

With 100% schema coverage the inputs are adequately covered, but there is no output schema and the description says nothing about the shape or nature of the returned second opinion, nor about the astra confirmation flow that the schema implies. Adequate but with clear gaps for a 6-parameter tool.

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 all six parameters are already documented in the schema, and the description adds no parameter-level detail beyond what is there. Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb (Consult) and resource (OpenAI Codex) plus the class of artifact it evaluates (architecture plans, refactoring strategies, trade-offs). This distinguishes it from codex_review_code and codex_debug_error reasonably well, but it never names a sibling explicitly, so the boundary against codex_analyze is left to inference.

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 implies a usage context — you consult it for a 'second opinion' on plans and trade-offs — which suggests it is a higher-level advisory call rather than a code-level review. However, it offers no explicit when-to-use/when-not guidance and never contrasts itself with the five sibling tools.

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