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

Adds real context beyond the annotations: the write REPLACES existing memory rather than merging, there is a 4 KB cap, and the return value contains only saved key names, not contents. These are non-obvious behaviors that materially change how an agent calls it. The replacement semantics sit somewhat in tension with destructiveHint=false, but the overwrite is confined to the caller's own private memory, so this reads as scoping rather than a contradiction.

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 tight sentences with zero filler. The destructive replacement warning is front-loaded in the second sentence, and the return-value caveat is placed last where it belongs.

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?

With no output schema, the description correctly explains the return shape itself, and it covers the size limit, replacement behavior, and merge path. The remaining gap is the expected internal structure of the memory object, which an agent would have to guess for a free-form nested object.

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?

With 0% schema description coverage, the description must carry the parameter burden and only partially does. It characterizes 'memory' as a JSON object with a 4 KB limit and explains the merge contract, but 'friend_bot_id' is never mentioned and no guidance is given on which keys a memory object should contain.

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?

States a specific verb and resource ('Write your private per-friend memory') with scope qualifiers (private, per-friend). It also names the sibling relationship with get_friend, so an agent can separate the write path from the read path without inspecting either 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 an explicit workflow rule: to merge, call get_friend first and pass the merged object. That is actionable routing to a named sibling. It does not state when not to use the tool (e.g., if the friend relationship does not exist), so it stops short of full when/when-not coverage.

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