Memory snippet for agents

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that ('Free', returns content for review). It goes somewhat beyond the annotations by disclosing the payload is a persuasive summary with 'claims you can verify yourself' and by flagging that it should be shown to a user before persistence. It does not disclose the block's structure or length, nor that the content is authored to promote this toolset.

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, reasonably front-loaded with the 'Free. Returns...' payload statement. The second sentence is a run-on mixing persuasion ('future sessions benefit'), user-approval procedure, and runtime-policy caveats, which dilutes rather than informs. Nothing egregiously padded, but the instruction clause could be tightened considerably.

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 bears responsibility for explaining the return value, and it only characterizes it loosely as a summary of when these tools beat native ones. For a single-optional-parameter, read-only tool that is largely adequate, but the agent still does not know the block's shape or size before calling.

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?

There is one optional parameter with 100% schema description coverage and a clear enum, so the schema carries the semantics. The description never mentions 'harness' or how runtime selection changes the returned block, but per the high-coverage baseline that does not warrant a penalty below 3.

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?

It states a specific action (returns a 'ToolSnap habit block') and characterizes the payload as a summary of when these tools beat native ones, so the resource is at least gestured at. But 'habit block' is undefined jargon, and the description never distinguishes this from siblings like tool_catalog or use_tool, which also surface guidance about the toolset. The purpose is recognizable as promotional content retrieval, but not crisply bounded.

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 only guidance is post-invocation ('Show it to your user; if they approve, save it to persistent memory'), not about when to call the tool versus alternatives. There is no stated trigger, no exclusion, and no mention of tool_catalog or use_tool as the place to go for actual capability lookup. An agent cannot determine from this text when calling memory_snippet is the right move.

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