Entity: Smart Select (semantic predicate)

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

Annotations already declare readOnlyHint=true, so the read-only nature is clear. The description adds context about using a 'predicate' for selection but does not disclose potential behaviors like performance impact or limitations on entity types.

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 sentence that conveys the core purpose without extra words. It is efficient; a slight improvement could be structuring to include key predicate keys.

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 one parameter, a well-documented schema, and an output schema present (not shown but indicated), the description provides the essential purpose. The tool is straightforward, and the description is adequate for an AI agent to understand its use.

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 100%, and the schema description for 'predicate' is detailed (keys, types, example values). The description only reiterates 'semantic predicate' without adding meaning beyond the schema, meeting the baseline.

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 'Select entities by semantic predicate instead of memorising handles' clearly states what the tool does (select) and the resource (entities). The predicate-based selection is distinct from other selection tools (e.g., entity_get, analysis_select_by_layer), though explicit differentiation is absent.

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 implies usage for cases where semantic filtering is needed (type, layer, etc.) but provides no when-not-to-use guidance or explicit comparisons to sibling tools. The absence of context exclusions leaves room for misuse.

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