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

No annotations, so the description carries the full burden. It discloses poll semantics, the awaiting_user_selection → committed/expired/cancelled lifecycle, recommended_poll_delay_ms with fallback and a 250ms floor, and that the response carries do_this_next/poll_loop. It stops short of auth requirements or expiry timeout behavior, keeping it below a 5.

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 tier tag and When/Prerequisites/Poll-loop/Next structure, which is scannable. It is dense and somewhat long, but nearly every clause conveys actionable routing or loop behavior 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?

For a polling tool with an output schema (which owns return-value detail), the description covers trigger, prerequisite, loop timing, terminal states, and next steps. The only gap is the second parameter and expiry specifics, which are minor given the output schema.

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 0% across 2 params, so the description must compensate. It explains where selection_task_id comes from (request_part_selection or active_selection_task_id in map session state) but says nothing about guidance_handle, leaving half the parameters undocumented in both places.

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+resource — poll/retrieve committed part IDs — and frames it against the sibling that precedes it (request_part_selection) and an alternative (get_map_selection). An agent can distinguish this from request_part_selection and get_map_selection without opening schemas.

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?

Explicit 'When' trigger, prerequisites (selection_task_id source, including the ezt://map-sessions state path), a concrete poll loop with status transitions, and a 'do not start a new selection' exclusion. It also names follow-on tools (realign, create_territory_from_parts, analyze).

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