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

Goes well beyond the annotations: it discloses that no file passes through the agent, that the call is asynchronous ('Returns a task') with ts_handle and designer_warnings in the result, and that supplying map_session_id replaces the open map's content — a state effect the destructiveHint=false annotation does not convey. It also names a specific failure mode (UNKNOWN_PART_LAYER) and the diagnostic payload (available_part_layers), which is exactly the kind of runtime behavior an agent cannot infer from structured fields.

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 core purpose and mechanism, then progressively narrower details, with zero filler sentences. It is written in a compressed, telegraphic register that borders on run-on ('part_layer forces the part layer'), which slightly hurts scannability but does not waste words.

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 seven-parameter, open-world, non-idempotent import with an output schema, it covers mechanism, prerequisites, the map-session side effect, and the notable error path, and it need not restate return fields since an output schema exists. The only gap is that it does not say how to retrieve the task result (tasks_get/tasks_result), leaving the async handoff implicit.

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 description coverage is only 29%, so the description carries most of the load, and it does cover all seven parameters in some form: the four include_* toggles 'narrow it', point_layers, part_layer forcing the part layer, map_session_id replacing the open map, and project_id's source. What it lacks is per-parameter precision — e.g. it never states defaults (all include_* default true) or what part_layer's string value looks like beyond the EZT part layer id mapping.

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: 'Opens an EasyTerritory Designer project as a Territory Solution,' and immediately clarifies the mechanism (server exports from Designer, then imports) so it is clearly the inbound counterpart to push_to_designer and distinct from import_geojson/import_dataverse_view. The content scope (territories with part_ids, point layers, routes) makes the artifact produced unambiguous.

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?

Gives concrete prerequisites ('Requires link_designer') and the upstream source for the key id ('project_id comes from list_designer_projects'), plus an explicit branch: pass map_session_id to replace the open map's content. It also prescribes a recovery path on UNKNOWN_PART_LAYER ('retry with the user's choice as part_layer'). It stops short of explicitly contrasting when to choose this over import_geojson or push_to_designer, so it is strong but not fully exhaustive.

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