poll_tasks

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

Annotations cover safety (readOnly, idempotent, non-destructive), and the description adds the behavior that actually matters here: it blocks until an assignment arrives or the timeout expires, and it reports whether a change occurred. That blocking/call-duration trait is not derivable from 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?

Five short sentences, front-loaded with the blocking semantics, then return behavior, then the backward-compatibility routing. Nothing is padded and no sentence repeats structured data.

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, the description carries the return-value burden and does: current assigned tasks, a change flag, and the lean-vs-full shape. Combined with the blocking contract, an agent has everything needed to call this 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 coverage is 100%, so the baseline is 3, but the description goes further by explaining what the lean view actually omits ('first-line descriptions, no envelope fields') and that full=true returns complete items — clarifying the trade-off the parameter controls rather than restating its default.

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 ('Long-poll for new task assignments') and immediately distinguishes itself from the sibling get_my_tasks by naming the non-blocking alternative. An agent can route between the two without opening either schema.

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 prefer it (legacy/backward compatibility) and when not to ('prefer get_my_tasks for non-blocking access'). The blocking-vs-non-blocking condition is exactly the decision an agent needs to make.

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