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

With no annotations, the description carries the full burden and discharges much of it: it discloses the asynchronous task model, the commit poll loop with recommended_poll_delay_ms, the directive never to ask the human to type 'committed/done/go', the dual-surface behavior (Apps host vs map_url tab), and connection prerequisites. It stops short of describing failure/expiry behavior despite an expiry_seconds parameter, so not a full 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?

Well-labeled and front-loaded with When/Prerequisites/Poll loop/Next sections, and most sentences carry operational content. It is nonetheless dense and repeats the commit poll loop point ("The commit poll loop above is identical on both surfaces"), adding mild redundancy given the length.

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 complex async human-input tool with an output schema, the description covers the workflow, prerequisites, polling contract, and follow-on tools an agent needs to orchestrate correctly. The remaining gap is parameter-level guidance across the 12-argument schema, which is not addressed.

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 12 parameters, so the description must compensate and largely does not. It only indirectly touches part_layer, active_tal_id ("active TAL when realigning"), and realign_operation; it says nothing about prompt, purpose, expiry_seconds, guidance_handle, new_territory, destination_territory_id, remove_empty_territories, user_id, or ts.

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 states a specific verb+resource – requesting human part selection on the map for realign, manual territory build, or return_list – and distinguishes this initiating tool from siblings like get_part_selection (polling) and get_map_selection (reading committed state). It is clearly not a tautology of the name, though the "[Tier 2 — Human Spatial Input]" prefix front-loads taxonomy rather than the plain purpose.

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-to-use (realign, manual territory build, return_list), prerequisites (MC-first, viewer connected, part_layer, active TAL when realigning), the user-initiated alternate path via the MC legend finger icon, and the follow-on tools (realign, create_territory_from_parts). It even names the alternative for reading an existing selection and says not to ask the human to re-select.

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