Open Kioku Remember Fact

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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false. The description adds that the fact is append-only, immutable, not deduplicated, survives re-indexing, writes to local storage, and is not idempotent. This provides critical behavioral context beyond the annotations, with no contradictions.

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 about 4 sentences, front-loaded with the main purpose. It covers all essential information without unnecessary fluff. While very efficient, it could be slightly more terse, but overall it balances detail and conciseness well.

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 has 3 parameters, an output schema, and annotations, the description is comprehensive. It covers usage guidelines, behavioral traits, parameter semantics, and even includes a recommendation to call a sibling tool. There are no gaps; the agent can fully understand how and when to use this tool.

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%, baseline 3. The description adds significant meaning: explains that 'text' should be a complete, self-contained statement with ~4KB limit; 'source' defaults to 'mcp'; 'confidence' has specific semantics ('low' for uncertain, 'exact' for verified truths). These details help the agent craft correct parameter values.

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 clearly states the tool persists a durable, repository-scoped memory fact into a SQLite store with optional source and confidence. It uses specific verbs ('persist', 'append') and resources ('local .ok SQLite store'), and distinguishes itself from sibling 'search_memory' by recommending to call it first to avoid duplicates.

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 explicitly specifies when to use (durable, repository-scoped facts like architectural decisions) and when not to use (transient session notes, per-task scratch data, facts derivable from live index). It also provides an explicit alternative: 'search_memory' to check for existing facts before recording.

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