Monitor a Jules session with progress

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

Annotations already establish that this is a read-only, non-destructive operation. The description adds genuinely useful behavior beyond those annotations: it emits MCP progress notifications during polling and returns the final session state and outputs. No contradiction with the 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?

Two sentences with no filler; every clause earns its place. The terminal-state polling behavior and progress-notitication detail are front-loaded ahead of the return-value note.

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 tool with no output scheem, it clearly states what is returned (final session state and outputs). It also specifies terminal states and the notification mechanism, giving an agent enough to know how the call behaves. The long-duration blocking aspect is conveyed by 'Polls ... until terminal state'.

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 input scheem covers 100% of parameters with descriptions for session_id and poll_interval_seconds, so the description need not repeat them. The description adds no semantic detail beyond the scheem, so baseline 3 is appropriate.

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 uses a specific verb ('Polls'), identifies the exact resource (a Jules session), and names the stopping condition (terminal state COMPLETED or FALED). This clearly separates it from one-shot peers like jules_get_session, and its polling-with-progress behavior sets it apart from jules_wait.

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?

Although 'Polls until it reaches terminal state' makes the use case apparent, the description does not mention alternatives such as jules_get_session or jules_wait, nor does it state when not to use this tool. The context is present but only implied, so it is not explicit enough for a 4.

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