remember_memory

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

Annotations already declare non-read-only, non-destructive, closed-world, and idempotentHint=false, so the safety profile is largely carried by structured data. The description adds real value with dedup behavior ("same entity/content is deduplicated") and attribution preservation, but it does not say whether a duplicate returns the existing record or an error, nor what permissions or side effects apply.

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?

Three short clauses, no filler, with the retry-safety guarantee front-loaded after the core action. It is efficient, though the density borders on under-specification given the parameter surface.

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?

For a 9-parameter write tool with no output schema and zero schema description coverage, the definition is too thin: return shape, duplicate-handling semantics, and most parameter meanings are unstated. An agent can call it, but cannot confidently predict the outcome.

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% across 9 parameters, so the description must compensate and largely does not. Only request_key (retry safety) and attribution ("unknown sources stay unknown") get any treatment; entity_name, content, kind, project, occurred_at, source_agent, and source_session are left entirely to bare type constraints.

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?

States a concrete verb and resource ("Save a confirmed useful memory with provenance") and adds distinguishing traits (retry safety, dedup) that separate it from correct_memory and forget_memory. "Confirmed useful" is a judgment call left unexplained, but the core action is unambiguous.

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?

Implies this is the path for durable facts and tells the agent to pass request_key for safe retries, but never says when to prefer it over correct_memory, add_observations, or create_entities in the sibling set. The agent must infer the routing decision.

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