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

Goes well beyond the annotations (which only say non-readOnly, non-destructive, non-idempotent): it discloses that the call returns a task, that the result carries geojson_artifact/share_url/download_url, that share_url is key-less and expires in one hour while download_url needs the API key, and that no inline body is ever returned. That is exactly the operational context an agent needs to invoke and follow up on this tool.

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 purpose, then filters, then inputs, then outputs — a logical order. It is dense but nearly every clause carries information; the only near-redundancy is restating the route feature/stop behavior that the schema already documents, and the dangling 'share_with_user' reference is slightly ambiguous.

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 and the description still covers the essential return contract (artifact vs. share_url vs. download_url) plus export composition and filtering, which is enough for an 8-parameter tool. Minor gap: the 'give the user share_with_user' instruction references something not defined in the schema or sibling list, leaving a small ambiguity.

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 already 88%, so the schema carries most parameter documentation, but the description adds a useful distinction: tal_ids/point_layers/route_layers 'narrow' the export while include_points/include_routes 'omit a family', which is a semantic layer beyond the field descriptions. It also clarifies that the three input identifiers are alternative entry points.

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 — exports a territory solution as a single GeoJSON file — and names the concrete payload (polygons with part_ids, points, routes with numbered stops). It is clearly distinguishable from siblings such as import_geojson, push_to_designer, and publish_to_dataverse.

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 the intended contexts (share, archive, open in Designer) and states the accepted input entry points (map_session_id, ts_handle, or a completed build job_id). It also implies the reverse operation via 'import_geojson reopens the file', but never explicitly says when to prefer this over export-adjacent siblings like publish_to_dataverse or push_to_designer.

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