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

Annotations only tell the agent this is a non-read-only, non-destructive write; the description adds genuinely non-obvious behavior beyond that — deduplication ('If the same fact is already saved, nothing is added'), the immutability of existing records, and an explicit safety prohibition ('Never save secrets such as passwords or keys').

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?

Front-loaded with the purpose and usage trigger, then layers behavioral and content-quality rules. Every sentence carries a distinct rule, though the 'Creates a new record; it does not change or delete existing memories' clause partially overlaps with the dedup statement that follows.

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 6-parameter mutation with annotations but no output schema, the description covers purpose, trigger, non-destructive scope, dedup semantics, safety, and content-authoring guidance. It does not say what a successful call returns (e.g. whether an ID or the created record comes back), which is the main remaining gap.

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 baseline is 3, but the description goes further by telling the agent how to author the two semantically important fields: keep `fact` concrete and standalone, and populate `entities` with every person/company/product/project/tool/topic the memory touches. It adds no guidance on `kind`, `confidence`, `importance`, or `source_title` beyond the schema.

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 specific verb and resource ('Save one new memory to the user's Locul account') and immediately scopes it as additive ('Creates a new record; it does not change or delete existing memories'), which cleanly separates it from the read-oriented siblings like recall_memories, search, and get_entity_profile.

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?

Gives an explicit trigger condition: 'Use only when the user asks to remember or save something.' That is a clear when-to-use rule, but it never names the alternative tools (recall_memories, search) for the retrieval cases an agent might otherwise conflate with this one.

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