Navigate the tab (LinkedIn only)

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

Annotations declare readOnlyHint=false (mutation) and openWorldHint=true. The description adds meaningful behavioral context: it navigates 'the human way (paced)', pauses the queue, and reports final URL, title, and checkpoint state. This goes beyond the annotations by explaining the pacing behavior and the queue interaction, which is valuable for an agent deciding whether to invoke this tool.

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 sentences with zero waste. The core action is front-loaded, the LinkedIn-only constraint is stated immediately, and the queue-pausing instruction is a critical operational detail that earns its place. Every word contributes to correct invocation.

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 the essential context: what it does, the scope constraint, the pacing behavior, the queue interaction, and what it reports back. The only minor gap is not explaining what 'checkpoint state' means or what the output format looks like, but with no output schema and a simple parameter, this is reasonably complete.

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 description coverage is 0%, so the description must compensate. The description mentions the URL must be a linkedin.com URL, which adds meaning beyond the schema's 'uri' format. However, it doesn't explain details like whether the URL must be absolute, whether redirects are followed, or what happens with non-LinkedIn URLs. The single parameter is simple enough that the description's LinkedIn-only constraint provides adequate but not complete semantics.

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 states a specific verb ('navigate'), a specific resource ('the working tab'), and a specific scope ('LinkedIn only'). It also distinguishes itself from generic navigation by noting the 'human way (paced)' approach and the reporting of final URL, title, and checkpoint state. This clearly separates it from siblings like debug_page_text or debug_find.

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 explicitly says to pause the queue first to avoid fighting the worker for the tab, which is a clear usage guideline. It also implies this is for LinkedIn URLs only. However, it doesn't explicitly state when NOT to use this tool versus alternatives like debug_page_text or debug_find, though the LinkedIn-only scope provides some implicit exclusion.

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