browser_keep_alive

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

With no annotations, the description carries the full burden and does well: it discloses the background pinger mechanism, that it replaces any existing keep-alive for the same tabs, and that the pinger auto-stops on bridge restart. It does not cover return values or failure modes, but the lifecycle behavior is unusually well documented for a side-effecting 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?

The purpose and mechanism are front-loaded in the first two paragraphs, followed by a workflow recipe and an args block. Everything earns its place, though the Args section is somewhat verbose for a two-parameter tool.

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?

With no output schema and no annotations, the description usefully covers lifecycle, replacement semantics, defaults, minimums, and the auto-stop on restart. The only gap is what the call returns or how to confirm the pinger is active, which is minor for a keep-alive tool.

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 0%, so the description must compensate and largely does: it explains interval_seconds has a 10s minimum and 60s default, and gives the tuning rationale ('well under Zen's unloader timeout, commonly 20+ minutes'). tab_ids is only restated ('Tab IDs to keep loaded') with no format hint, which holds it below a top score.

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 opens with a specific verb and resource ('Keep tabs warm so Zen's Tab Unloader won't discard them') and explains the mechanism (background pinger firing no-op JS evaluations). It also names its sibling browser_keep_alive_stop and the related browser_parallel, letting an agent distinguish it from generic tab tools.

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 gives an explicit when-to-use recipe: 'Use this at the start of parallel multi-tab work: open your tabs, call browser_keep_alive with their IDs, drive them in parallel... then browser_keep_alive_stop when done.' Both the trigger and the terminating alternative are stated, leaving nothing to inference.

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