codex_list

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

The readOnlyHint annotation already covers the safety profile, and the description adds useful context about local scope and returning summary/identity rather than full content. It does not disclose pagination behavior, how query/cursor influence results, or behavior on empty/no-match results, which are relevant for a listing tool.

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 short sentences front-load the core behavior and then add the essential kind enum. There is no filler or redundancy.

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?

The output schema covers return structure and annotations cover the read-only nature, but the description leaves query/cursor behavior and alternative-tool routing unspecified. It is adequate for simple default-limit calls, but not fully complete for non-trivial use.

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 explicitly enumerates valid kind values, which is valuable, but it does not explain limit, query, or cursor semantics beyond their names and defaults; the parameter documentation remains incomplete.

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 identifies a specific action (只读盘点/read-only inventory) on a specific resource (本机 Codex 来源) and the return shape (摘要与原文身份). It is clear, but it does not explicitly contrast itself with sibling tools such as codex_read or codex_groups, so it stops short of full sibling differentiation.

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 intended usage—read-only inventorying of local Codex sources—is implied clearly, and the kind list defines the categories. However, the description never states when to choose this over alternatives like codex_read, codex_import, or codex_groups, nor mentions any exclusions.

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