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

With no annotations, the description carries the full burden and delivers: the server loads the session TS, appends a new TAL, and rebinds the session before map_refresh; new TALs do not inherit dwell_time; missing dwell causes workload_omitted in Analyze; declining an in-band dwell prompt still permits creation (HITL-038). These are genuine side effects and failure semantics beyond any structured field.

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 useful headers (When/Prerequisites/Next/Dwell/Scenarios), but the body is very dense and acronym-heavy (TAL, TS, MC, RL, HITL, DWELL), which taxes readability. Several clauses about downstream Analyze behavior and prompting could be tightened without losing meaning.

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?

An output schema exists, yet the description still usefully names key return fields (created_territory.territory_id, leaf_territories, selection_summary, map_refresh.notified) and the realignment rule that must use territory_id rather than an invented shorthand. It covers the workflow end-to-end; the remaining gap is the five undocumented input parameters.

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 10 parameters, so the description must compensate. It meaningfully explains part_ids, part_layer, map_session_id, dwell_time and the display-only nature of territory_name, but says nothing about ts, tal_id, territory_path, conflict_policy, or guidance_handle — roughly half the parameters remain 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+scope: 'create or update one leaf territory from committed part IDs', and tags the trigger conditions (manual MC-005 build, RL-011/012). It is clearly distinguishable from siblings like auto_build, direct_build, realign and territory_merge, which are named or implied by contrast.

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:', 'Prerequisites:', and 'Next:' sections, plus a negative instruction ('do not call get_map_visualization just to show the new territory') and a routing rule for when to call it (rebind_required / notified=false). Alternatives such as analyze and realign are named with the condition that selects them.

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