remember

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

Annotations already declare a non-readonly, non-destructive, non-open-world write; the description adds materially beyond them: writes only to the local database, nothing leaves the machine, raw media bytes are discarded, and the return payload includes the id required by 'forget'. That last point is operationally critical for chaining calls and appears nowhere in the annotations.

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 core action, then context parameters, then the recall rationale, then side effects and returns – a sensible reading order with no filler sentences. It is dense and slightly run-on as one paragraph, which costs a point on structure but not on usefulness.

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 10-parameter write tool with no output schema, the description covers what is needed: what gets persisted, what is deliberately not persisted, that the call is local-only, and the shape of the return value including the id. Nothing an agent needs in order to call it correctly and use the result is missing.

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%, so the baseline is 3; the description earns an extra point by explaining the design intent behind parameters rather than restating them – place (geohash or lat+lon), time with local offset defaulting to now, salience as 'how much it matters', and the fact that content text is also embedded as the text channel. It stops short of describing precedence rules (geohash over lat/lon) that the schema itself carries.

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 opening sentence gives a specific verb and resource (store a memory) plus the defining twist (together with its sensory context) that separates it from 'sense' (raw readings) and 'recall' (retrieval). An agent can route between remember/recall/sense without opening any schema.

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 states the use case concretely: 'experiences, facts or decisions worth recalling in a future situation', and explains the consequence of omitting context ('a memory stored without place or time can only come back through its text'). It does not explicitly name 'recall' or 'sense' as the alternatives, nor say when not to use it, so routing still requires a small inference.

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