Entity: Smart Select (semantic predicate)

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

The readOnlyHint annotation already indicates safety; the description adds "Uncapped" (no result limit) and a practical tip about the typical return field, which gives useful behavioral context beyond 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?

Exactly two sentences, each earning its place: one states the operation, the other a usage tip. No fluff or redundancy.

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?

With a rich schema, output schema, and readOnlyHint, the description provides the essential context: semantic selection, uncapped results, and typical next step. The tool is fully usable from these instructions.

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 fully documents all parameters, so baseline is 3. The description adds the recommendation fields=['handle'] for the common dimension workflow, which provides semantic guidance beyond the raw 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?

Clear: "Select entities by semantic predicate" specifies a query operation, and "instead of memorising handles" distinguishes it from handle-based retrieval. However, it doesn't explicitly name sibling tools like entity_get or selection_filter, so it doesn't fully differentiate from them.

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 actionable context: use when selecting by semantic criteria rather than handles, and the "usual next step is dimension_auto(handles)" pipeline tip implies a common workflow. No explicit exclusions or alternative tool names, but the guidance is concrete.

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