memory_fact_get

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

Even with no annotations, the description discloses critical behaviors: case/separator-insensitivity, null meaning, set-valued slot representation, return shape (record, contenders, entity_ref), and semantics of 'candidates' as leads not answers. This is highly transparent for a getter.

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 dense but efficient: main purpose first, then set-valued exception, then return semantics. Every sentence contributes new information with no fluff or repetition.

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?

Given the output schema exists, the description still goes beyond it by clarifying edge cases and return semantics. It covers null vs empty, set values, conflicts, and nearby slots, making it complete for an AI agent to decide when and how to invoke.

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 adds meaning by explaining that entity and attribute form a slot and are case/separator-insensitive. It doesn't give explicit format examples but provides enough context for the two string parameters.

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 opens with a specific verb and resource: 'Look up the one CURRENT value at an (entity, attribute) slot.' It clearly scopes the action and distinguishes it from nearby tools by contrasting with memory_search and memory_fact_resolve.

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?

Explicitly directs when to use alternatives: memory_search for context, memory_fact_resolve for unresolved conflicts. Also clarifies that a null record means EMPTY, not unknown, which guides the agent to search elsewhere when needed.

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