memory_fact_set

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It richly explains the write behavior: history is kept, new values supersede old, conflicting writes are parked as contenders with action='contested', winner under 'current', and suggests human check and settlement via memory_fact_resolve. It also discloses defaults for optional parameters and the return shape. This goes well beyond what the schema reveals.

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 structured with a clear title line, a concise behavior summary, a compact args reference, and a returns line. Every sentence adds unique value: conflict handling, parameter defaults, and output format are all covered without fluff. It packs substantial information into a small space, making it easy for an agent to scan and apply.

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 tool's moderate complexity (7 params, 3 required, conflict behavior, output schema), the description is remarkably complete. It covers the action's purpose, conflict semantics, parameter meanings, defaults, and return values. It also cross-references a related tool for conflict resolution, which helps the agent understand next steps. No critical information appears missing for safe and correct 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 description coverage is 0%, so the description must compensate. It adds meaning for origin ('user' vs 'action'/'agent'), confidence (0..1 default 0.8), episode (attribution handle), and freshness_class ('auto' infers decay). However, it does not explicitly define the required parameters entity, attribute, and value, though they are implied by 'slot' and the tool's purpose. Overall, it provides meaningful semantics for several parameters but leaves some required ones implicit.

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: 'Assert a canonical fact — insert, confirm, or correct a slot.' It clearly distinguishes itself from reading tools (memory_fact_get) and resolution tools (memory_fact_resolve) by explaining the write/update semantics with conflict handling. This leaves no ambiguity about what the tool does.

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 clear behavioral context, such as how new values supersede old ones and how conflicting writes become contenders requiring human check, then points to memory_fact_resolve for settlement. It does not explicitly name alternatives like memory_store, but the conflict-resolution guidance implies when this tool is appropriate. The inclusion of default values for origin, confidence, and freshness_class further aids invocation.

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