authorize_oauth

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

With no annotations, the description carries the full burden of disclosing side effects and required permissions. It only mentions a return dictionary and does not explain that starting an OAuth flow typically involves external interactions, potential user involvement, or state changes. No permissions or rate limits are mentioned. 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?

The description is compact and well-structured with an Args section and Returns section. It avoids unnecessary detail and is easy to skim, making it efficient for an agent to parse.

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 tool has an output schema, so return values are covered. However, the description lacks essential context around prerequisites (e.g., whether a provider must be pre-configured), the nature of the OAuth flow (interactive, redirects, external calls), and any postconditions. For a complex tool like OAuth authorization, this leaves the agent under-informed.

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?

The parameter 'provider' is given clear semantics and examples ('github', 'gdrive') in the description, which the schema does not provide (only 'Provider'). This helps the agent select appropriate values, though the description could have listed more provider options or referenced the list_oauth_providers tool.

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 clearly states the tool's action (start OAuth authorization flow) and its target (a provider like 'github' or 'gdrive'). It distinguishes itself from sibling tools like revoke_oauth, which performs the opposite action, and list_oauth_providers, which merely lists providers.

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 provides clear context for when to use the tool: to initiate OAuth authorization for a provider. However, it does not explicitly mention alternatives or exclusions, such as 'use revoke_oauth to undo' or 'only works for providers listed in list_oauth_providers'. This is sufficient but not fully explicit.

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