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

Discloses substantial downstream behavior beyond the annotations: with a boundary the country is derived 'from where the land lies', the forest record is 'warmed', and the land check runs when the crop is EU-regulated; with only a pin, mapped fields are surfaced as suggestions for a person to accept. It also states the write happens and explains the join_m default (3 m each way) and neighbor-joining logic.

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?

Purpose is front-loaded in the first sentence, and subsequent sentences earn their place by covering each input mode. It is a long, dense paragraph with jargon ('closing the bunds and tracks between neighbours') that could be broken up, but little of it is 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?

An output schema exists, so return values need not be explained. For an 8-parameter, nested-object creation tool the description covers the main input paths (name, crop, country, pin, boundary, fields, join_m) and the triggered side effects, leaving only minor gaps such as constraints on the separate pieces when fields are far apart.

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?

With schema coverage at only 38%, the description compensates well: it clarifies boundary is a GeoJSON Polygon/MultiPolygon 'longitude first', that fields are multiple outlines joined into one farm, and that join_m defaults to 3 m per side. Minor gap: lat/lon are only described as a 'pin (lat, lon)' without reinforcing valid ranges.

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 upfront: 'Add a farm to this organisation's record.' An agent can distinguish this creation tool from siblings like eudr_set_farm_boundary or eudr_list_farms, since the description explains it accepts a boundary at creation time rather than only setting one later.

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 clear conditional guidance on input modes: 'A name is enough', supply crop/country/pin 'when known', use boundary for a known outline, fields for joining parcel outlines. It lacks explicit routing against sibling tools (e.g., when to prefer eudr_set_farm_boundary afterwards), so it stops short of the top band.

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