memory_remember

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

With no annotations provided, the description carries full burden. It reveals the tool returns a fact id and implies persistence, but does not disclose potential side effects (e.g., overwrite behavior), required permissions, error handling, or whether it can fail silently.

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?

Two sentences front-load the purpose and usage context, with no redundant phrases. Every sentence serves a distinct function: purpose, usage guidance, sibling differentiation, and return value note.

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 parameter set (5 params, 3 required) and absence of output schema, the description covers the basic lifecycle (add, return id, forget). However, it omits details like whether adding duplicate facts creates duplicates or updates, and doesn't discuss scope isolation or session behavior beyond the schema.

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 100%, so the schema already explains all parameters. The description adds minimal meaning beyond the schema (only linking to `save_outcome` and `memory_forget`). Baseline 3 is appropriate as the description does not materially enhance parameter understanding.

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 'Explicitly add a fact to persistent memory' with a specific verb ('add') and resource ('fact'). It distinguishes from the sibling tool `save_outcome` by contrasting explicit vs implicit extraction, and notes the return of a new fact id for use with `memory_forget`.

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?

It explicitly states when to use: 'when the user says something the engine should remember across sessions' and provides examples. It mentions the complementary role of `save_outcome` and tees up `memory_forget` for the returned id, but does not explicitly list non-usage cases or other alternatives.

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