Remember

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

Discloses the dedup/upsert behavior explicitly ('Identical memories are updated, not duplicated'), which is real behavioral context and consistent with idempotentHint=true. It does not contradict the annotations, though it adds nothing about what happens to a memory when its files change beyond the schema's own note.

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 sentences, no filler, and the purpose is front-loaded before the constraints. Every sentence earns its place: purpose, content shape, dedup semantics.

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 4-parameter write tool with no output schema, the description covers purpose, content expectations, and idempotency. The one gap is what a successful call yields (an id? a confirmation?) and how it interacts with confirm_memory, which an agent would have to infer.

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 75% and the description meaningfully supplements it: it expands the kind enum into prose categories and, more importantly, explains the intended content of the required field and why it must be self-contained. tags and files are left to the schema, which documents them adequately.

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?

Clear verb ('Save') plus the exact resource and audience ('something future sessions on this project should know'), and it enumerates the accepted kinds. An agent can distinguish it from recall, forget, list_memories, and confirm_memory 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?

Gives strong positive guidance on what belongs in a memory (a decision and why, a convention, a gotcha, a fact, a todo) and the shape it should take ('one self-contained statement'). It never names a sibling alternative or a when-not condition, but the context is unambiguous enough that routing is easy.

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