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

No annotations are provided, so the description carries the full burden — and it delivers. It discloses the deterministic/no-LLM nature, exactness, lon/lat order detection with a `note` flag, error-on-ambiguous-input behavior with concrete hints ('never a guess'), and the exact JSON return shape ({ok, kind, label, lat, lon, note, ...}). Nothing about behavior is left to inference.

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?

The description is long but densely informative; the format enumeration is necessary for a parser of this breadth, and the behavioral/return notes are all load-bearing. It is front-loaded with the core purpose. Only mild trimming would be possible without losing value, so it earns a 4 rather than a 5.

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?

Despite the schema being minimal (a single string param), the description covers accepted input formats, order detection, error semantics, determinism rationale, and the full return contract. The output schema isn't shown, so the description's JSON shape documentation fills that gap. Nothing an agent needs to call and interpret this tool is missing.

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%, so the description must compensate — and it thoroughly documents the single `text` parameter by enumerating every accepted format (decimal with separators, EU comma, DMS, DDM, NMEA, UTM, MGRS, British grid, Geohash, Plus Codes, map links). The agent knows exactly what input is valid without opening any schema.

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?

Opens with a specific verb+resource ('Parse ANY single coordinate string... into WGS84 lat/lon') and enumerates the full set of supported formats (DMS, DDM/NMEA, UTM, MGRS, Geohash, map links). This clearly distinguishes it from coordinate siblings like convert_coordinates, format_coordinate, and detect_coordinate_order — an agent immediately knows this tool accepts arbitrary human-pasted input.

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?

The phrase 'a human might paste' gives a clear usage context, and the determinism note ('LLMs are unreliable past 2-3 decimals; this is exact') tells the agent when this tool is preferable. However, it never names sibling tools (detect_coordinate_order, convert_coordinates) as explicit alternatives, so the routing is implied rather than stated.

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