remember

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

With zero annotations, the description carries the full behavioral burden and does so well: it discloses persistence across sessions, that stored content is injected into the system prompt, that the tool is write-only, and crucially the upsert behavior ('Writing a key that already exists corrects it in place'). The only notable gap is that it never states what a successful call returns or how the agent confirms success, which matters given there is no output schema.

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?

The description is front-loaded with purpose, then builds logically through storage criteria and parameter formats, ending with the critical upsert warning. At roughly 130 words it is longer than minimal, but every sentence earns its place: the examples clarify otherwise abstract criteria and the exclusion list prevents misuse.

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 three-parameter write tool with no annotations, no output schema, and 0% schema coverage, the description covers the essentials an agent needs to call it correctly: valid topic values, key formatting, upsert semantics, and content qualification. The main omission is the return/confirmation behavior, and the topic value set is stated in prose rather than enforced as an enum, leaving room for an agent to invent an invalid value.

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%, so the description must compensate. It explicitly documents topic ('one of printer, preferences, outcomes') and key ('short lowercase slug' with examples and correct-in-place semantics), but the note parameter is only implied as the fact content, never named or formally tied to the schema. The compensation is strong for two of three parameters and leaves the third to inference.

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 opens with a specific verb+resource ('Keep one fact for future sessions') that clearly states the tool's function, and immediately distinguishes it from the read-oriented siblings by declaring 'this is for writing, not reading.' It does not explicitly name forget as the inverse sibling, but the write-vs-read framing is sufficient to separate it from the lookup tools in the sibling list.

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 explicit inclusion criteria ('what will still be true next week' with concrete examples) and explicit exclusion criteria ('Not what you can look up — a preset value, a setting's range — and not what happened this turn'). The exclusions map cleanly onto the sibling lookup tools even though no tool is named directly, and no guidance is given for when to use forget instead.

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