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

The readOnlyHint annotation already establishes this is a safe read operation, and the description goes beyond it by exposing the internal decision flow: cheap loc_id path answers first, crosswalk evidence second, polygon geometry only as fallback. It also discloses the return categories (topology, geodesic intersection area, directional overlap shares) and notes that temporal validity and successor context are independent of the evidence source — useful behavioral context not present in the schema or annotations.

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?

Five sentences, each carrying a distinct piece of information: core purpose, fast-path sources, geometry fallback, return content, and a routing hint. It is dense and front-loaded. The only minor waste is the vague opener 'Smart relationship tool' and the somewhat redundant 'No payment required' note, but they do not meaningfully hurt readability.

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 complex comparison tool with 9 parameters, no output schema, and many siblings, the description covers the processing pipeline, fallback behavior, and key return values. It does not describe the outbound shape of the result structure, but the mention of topology, area, and overlap shares gives the agent enough grounding to invoke it and interpret the response. The annotation already covers the read-only safety profile.

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 100%, so the parameters are already fully documented. The description adds domain framing around loc_id paths and temporal validity, but it does not explain individual parameter formats, defaults, or the anyOf batching structure beyond what the schema already provides. The baseline of 3 is appropriate.

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?

The description names a specific operation — comparing two geographic identities — and details exactly what kinds of relationships it answers (Admin Spine containment, common ancestry, crosswalk evidence, polygon overlap). This makes it clearly distinguishable from sibling tools like resolve_point, get_geometry, and identify_reference_system, all of which solve different problems.

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 description provides a direct routing instruction: 'Use convert_reference first for names or outside identifiers.' This tells the agent when a sibling tool is the right antecedent. It implies this tool should be used for loc_id-based comparisons, though it does not exhaustively enumerate when not to use other geometry or resolution tools.

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