set_relation

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

Annotations already mark the tool as not read-only, so 'Record or update' is consistent but adds little beyond readOnlyHint=false. The description does not disclose important mutation behaviors such as action=remove, overwrite semantics, the bidirectional inverse-relationship effect, or idempotency, which are meaningful for a state-changing 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?

The description is a single front-loaded sentence that immediately states the action and resource. The relation list is somewhat redundant with the schema enum, but it is compact and helps at-a-glance understanding without bloating the text.

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 9-parameter write operation with no output schema, the description covers core purpose but leaves key behavioral semantics like the 'remove' action and 'bidirectional' flag to be discovered in the schema. Since the schema is rich and well-described, this is acceptable but not fully complete.

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%, with each parameter already documented, including enums for relation and action. The description's relation examples echo the schema enum rather than adding new semantic meaning, so the baseline score 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 identifies a concrete action ('Record or update') and a clear resource ('spatial relationship between two entities'), with a helpful list of relation types. It is clearly distinct from read-oriented siblings like get_spatial_map or query_entities, though it doesn't explicitly differentiate from update_entity and omits the 'remove' action shown in the schema.

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 intended use is implied: use this tool when a spatial relationship between two entities needs to be recorded or updated. However, there is no explicit when-to-use vs. when-to-use-another tool guidance, and siblings like update_entity or manage_spatial_spec could plausibly overlap, leaving selection partially to inference.

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