memory_put

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

Beyond the annotations it discloses the material behaviors: local NIP-44 encryption so the server holds only ciphertext, overwrite semantics on key reuse, a 1 MB per-agent-key quota whose exhaustion causes failures until delete or expiry, and the return payload. The overwrite behavior sits in mild tension with destructiveHint=false, but it is disclosed rather than hidden, so an agent is not misled.

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?

Purpose comes first, then constraints, then security model, then capacity limit, then the read pointer and return value. Every sentence carries operational information an agent needs before calling; nothing is filler.

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 this covers everything an agent must know: format limits, encryption and trust model, overwrite behavior, quota failure mode, and TTL defaults. The presence of an output schema means return values need no further expansion.

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 schema already documents key format, value size and ttl_days defaults, and the description largely restates those constraints (1-128 chars, 32 KB, default 90/max 366). It adds real meaning only for value ('encrypted on this machine ... before upload'), which is modest value on top of a fully documented 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?

The description opens with a concrete verb and resource ('remember something across sessions or machines') and immediately distinguishes itself from the read path by naming memory_get. An agent can tell this is the write side of a persistent key-value store without opening the 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 (persisting something across sessions or machines) and explicitly routes reads to memory_get, which is the relevant alternative among the siblings. It stops short of explicit when-not-to-use guidance, e.g. what belongs in memory versus board posts or profile fields.

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