poll_subscription

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

With no annotations, the description must disclose behavioral traits. It reveals that the per-subscription cursor advances atomically, ensuring no duplicate events are returned on successful polls. It also states that the filter is immutable after registration. This is good, but it could mention error handling or what happens if subscription_id is invalid.

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 description is three sentences, all essential. The first sentence states the core action, the second explains the cursor behavior, and the third clarifies constraints. No unnecessary words, and the most important information comes first.

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?

The description covers the tool's purpose, constraints, and behavioral guarantees. It doesn't describe the return format (e.g., array of events), but given that there is no output schema and the parameters are simple, the description is largely complete. A slight addition about return structure would make it a 5.

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 describes both parameters with 100% coverage. The description adds value by explaining why two expected parameters (since_seq, event_filter) are absent, clarifying server-side management. This contextual insight goes beyond what the schema provides, earning a score above the baseline of 3.

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 drains events for a server-side subscription, using specific verb and resource. It distinguishes itself from sibling tools like poll_events by clarifying that cursor and filter are server-managed, making the purpose unambiguous.

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 provides explicit guidance on when to not use this tool: it explains that there is no since_seq parameter (cursor is server-side) and no event_filter parameter (filter is set at registration). This tells the agent to re-register for a different filter. However, it doesn't compare directly to other polling tools, which would elevate to a 5.

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