Open the Facebook login window

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

Beyond the readOnlyHint annotation, the description reveals important behavioral traits: it 'only watches for the session to go live,' reports immediately if already logged in, and on timeout 'the window stays open and their progress is not lost.' No contradictions with 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?

Three sentences, front-loaded with the main action, and each sentence serves a purpose: launch, wait, safety, and timeout handling. 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?

For a single-parameter tool with no output schema, the description covers all relevant scenarios: success, already logged in, timeout, and fallback options (call again or check session). The agent receives enough information to invoke correctly and interpret outcomes.

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 already covers wait_seconds fully (100% coverage). The description adds context by explaining what happens when the parameter expires (e.g., 2FA code, checkpoint) and advises calling again, enriching the parameter's functional meaning.

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 function: 'Launch the browser, bring the window to the front on Facebook, and wait for the user to log in by hand.' It distinguishes from siblings like check_facebook_session by specifying it watches for the session to go live rather than merely checking it.

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?

Provides explicit usage guidance: safe when already logged in, and if more time is needed, 'simply call it again or run check_facebook_session.' It also clarifies it 'types nothing and submits nothing,' indicating it is not for automated login, thus steering agents to use it as a waiting/reporting tool.

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