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

Beyond annotations (which already say this is a write, idempotent, non-destructive), the description adds that memory is 'scoped by your identifier' and that anonymous sessions only retain data for 24 hours, which is critical behavioral context. This aligns with annotations and enriches the agent's understanding of side effects.

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 compact: a single opening sentence stating the core function, then a usage clause, then storage details, then a pairing tip. No redundant phrasing; all sentences add value.

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 simple 2-param tool with no output schema, this description covers the essential purpose, usage context, persistence behavior, and companion tools. It is fully sufficient for an agent to understand when and how to use it.

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% with clear descriptions and examples for both key and value, so the baseline is 3. The description adds minimal parameter-level detail beyond noting the key-value structure, though the usage examples implicitly show how parameters map to real tasks. No further elucidation is needed.

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 'Save' and identifies the resource as 'data the agent will need to reuse later,' clearly distinguishing this as a memory write operation. Examples like 'resolved ticker' and 'target address' illustrate concrete uses, and mentioning recall/forget as companions differentiates it from sibling tools.

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?

Explicit usage guidance is given: 'Use when you discover something worth carrying forward...' This tells the agent when to invoke it, and the pairing with recall/forget indicates when to use alternatives. The mention of persistence for authenticated vs anonymous sessions also helps decide when relying on memory is safe.

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