ask-gpt

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

Annotations already declare readOnlyHint=true, and the description adds 'advisory' and 'single-shot', confirming no state modification and clarifying it is a stateless one-query tool. This goes beyond the basic annotation without contradicting it.

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 two sentences and front-loaded with the core purpose. It is concise and efficient. However, the structure could be improved by listing key parameters or providing a quick example.

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 6 parameters, 0% schema coverage, no output schema, and multiple sibling tools, the description is incomplete. It does not explain return values, how `files` works, or the effect of `reasoningEffort`. The context is sufficient for a very simple tool but not for this complexity.

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?

With 0% schema description coverage, the description is the sole source of parameter meaning. It only explains `expert` ('apply one of the expert personas') but does not describe `prompt`, `developerInstructions`, `cwd`, `reasoningEffort`, or `files`. This leaves most parameters unclear.

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 clearly states 'Single-provider second opinion via codex (advisory, single-shot)'. It specifies the verb (ask/advisory), resource (codex/GPT), and scope (single-provider). However, it does not explicitly differentiate from sibling tools like ask-gemini or ask-grok, which are also single-provider tools.

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 usage as a second opinion tool ('advisory, single-shot') and mentions passing the `expert` parameter. But it lacks explicit guidance on when to use this over siblings (e.g., ask-all, ask-one) or when not to use it. No alternatives or exclusions are provided.

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