remember_context

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

With no annotations, the description carries the full behavioral burden. It does convey the core write side effect and the non-Garmin scope, but it does not mention overwriting behavior, retention, how effective dates interact with the stored memory, or what happens after recording. This is adequate but only partially transparent.

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 with no filler. The purpose is front-loaded and the trigger is stated in the second sentence. Every sentence contributes useful information without repeating schema details.

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 low-complexity four-parameter write tool, the schema already documents the parameters and the description covers why and when to use it. The main gap is that the optional effective_from/effective_to fields are never connected to the 'race and its date' example, and there is no mention of the expected confirmation or return behavior, but this is not blocking.

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. The description's enumerated examples mirror the kind enum and add no real meaning beyond what the schema already provides, and it says nothing about the optional effective_from and effective_to fields beyond what the schema states.

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 uses a specific verb ('Records') with a clearly scoped resource ('something about the user that Garmin does not know') and enumerates the exact kinds of things it stores. This distinguishes it from the read-only getter siblings and clarifies that it is a write/memory operation.

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 gives an explicit trigger: use it whenever the user mentions one of these things in passing. However, it does not name alternatives or state when not to use it, so an agent is not fully guided on routing between this, log_subjective, and get_user_context.

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