refresh_browser_cookies

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

With no annotations, the description carries the full burden. It discloses the main behavior (extract and save cookies), the browser-scanning logic, the difference for Firefox, and the return format. However, it does not mention potential side effects like overwriting existing cookies, permissions required, or failure modes (e.g., browser locked). It is honest about what it does but lacks depth on caveats.

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 well-organized with explicit 'Args' and 'Returns' sections, and it front-loads purpose and usage. It is a bit long due to the browser option list, but every sentence is informative. Slightly more compact could be achieved with a table, but current structure is clear and scannable.

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 the tool's simplicity (single optional parameter), the description covers what the tool does, when to use it, prerequisites, all parameter choices, and a basic return description. It does not detail error conditions or edge cases (e.g., what happens if no browser is found), but it is adequate for the tool's complexity. The existence of an output schema mitigates the need for richer return details.

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 schema only defines 'browser' as a string with a default, with 0% coverage. The description fully compensates by listing all valid options ('auto', 'arc', 'chrome', etc.), explaining what 'auto' does, and noting the Firefox difference. This adds critical meaning beyond the bare schema, making it easy for an agent to choose the right value.

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 immediately states the action ('Extract and save session cookies') and the resource ('from your web browser'), and ties it to a specific trigger (authentication fails for MyFitnessPal). This clearly distinguishes it from all sibling tools, which are all MFP data operations. The verb and resource are explicit and unambiguous.

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?

It explicitly states when to use: 'Use this tool when authentication fails and you need to refresh your MyFitnessPal session.' It also gives a prerequisite (must be logged into myfitnesspal.com). It does not mention alternatives or when not to use, but since there are no similar sibling tools, the context is sufficient. Lacks explicit exclusions, so not a full 5.

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