doctor

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

Annotations already indicate read-only/idempotent behavior. The description adds valuable context that deep mode is 'help-only surface checks' and consumes no model quota, which is a meaningful behavioral trait not present in 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?

Two concise sentences: the first states the purpose, the second clarifies the deep mode behavior. Every word earns its place; 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?

For a read-only diagnostic tool with an output schema, the description covers purpose, safety, and deep-mode behavior. However, it leaves workspace unexplained and does not elaborate on what the diagnostics actually produce or how to interpret them, though the output schema partly offsets this.

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 coverage is only 50% (workspace lacks a description). The description adds slight detail on deep (no model quota) but completely omits any explanation of the workspace parameter, which remains ambiguous. The description should compensate for the missing schema description but does not.

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 uses a specific verb 'report' and clearly names the resource 'setup diagnostics', listing concrete items (plugin version, Codex CLI resolution, login status, recursion guard). This differentiates it from action-oriented siblings like delegate and cancel.

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 context is clear: this is for diagnosing setup. The deep=true behavior is explained with a safety note ('no model quota'). It doesn't explicitly say when not to use it or mention alternatives, but the sibling tools are obviously different actions.

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