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

Annotations only give readOnlyHint=false and openWorldHint=true; the description adds the critical operational traits: it consumes a browser slot and may queue, a wait timeout means still-running rather than failed, and a successful run clears the checkpoint breaker. This is exactly the context annotations cannot express.

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?

Front-loaded with the core action, then layered with nuance about reactivity, queueing, and recovery. Dense and mostly earns its length, though the reactive-health explanation is slightly long-winded for a definition field.

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?

No output schema exists, and the description compensates by explaining what results mean (session dead vs. timed-out still-running) and the downstream action. An agent has everything needed to call and interpret it correctly.

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 100%, so sessionId and sessionLabel semantics (including 'never guessed' and the label alternative) are already documented in the schema. The description adds nothing about parameter format or precedence, so baseline 3 applies.

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?

States a specific verb and resource: runs a real session check for one account through the worker browser and records the result. It distinguishes itself from the passive status siblings (li_session_status, li_account_activity) by emphasizing 'REACTIVE' and 'real session check'.

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?

Explicitly says when to use it ('Check now' for the daily health routine, and to CONFIRM a reconnect took because it clears the checkpoint breaker). It also names the follow-up alternative, li_login_link, for the case where the session is dead.

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