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

Annotations declare readOnlyHint=false, which is non-obvious for something called a 'poll'; the description resolves this by disclosing that Tango persists a cursor and that repeated calls return only new items, plus the advance_cursor peek mode. It adds meaningful stateful-behavior context beyond the annotations, though it says nothing about rate limits or response shape.

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 first word 'Cursor-based poll:' front-loads the mechanism, the return contents follow, and usage cadence ends the description. It is dense but not padded; the trailing API reference URL is useful rather than filler.

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?

There is no output schema, so the description must convey what comes back, and it does by listing the three return categories and the incremental cursor semantics. Missing detail on response structure/pagination keeps it just short of full completeness.

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?

With 75% schema description coverage, the schema already documents worker, since, and advance_cursor, and the description only reinforces the cursor semantics ('since your last check-in'). The undocumented 'limit' parameter gets no explanation in either place, and the description adds no syntax detail beyond what the schema states.

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?

It names a specific verb and mechanism ('Cursor-based poll') and enumerates exactly what is returned: tasks newly assigned to you, tasks whose client/project context changed, and revised context objects. This is enough to distinguish it from siblings like pull_next_task, list_my_tasks, or check_in-adjacent reads without opening any 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?

It gives explicit cadence guidance: 'Call this at the start of every session or turn, and on your polling interval,' which tells the agent when to invoke it. It does not name a competing alternative or a when-not condition (e.g. versus pull_next_task or get_polling_instructions), so it stops short of full routing guidance.

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