Stateless Agent Memory Engine (SAME)

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

The annotations provide destructiveHint=true, but the description adds valuable behavioral context beyond this: it explains that notes are 'written to disk and indexed automatically,' mentions the 'SAME' system for stale detection when sources change, and describes how agent attribution is stored in frontmatter. This provides implementation details not captured in the single annotation.

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 efficiently structured: a clear purpose statement upfront, followed by key behavioral details, then a parameter summary. Every sentence adds value - none are redundant or verbose. The information is well-organized and appropriately sized for a tool with 5 parameters.

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 destructive write operation with no output schema, the description provides good context: it explains the write behavior, indexing, provenance tracking, and confirms what's returned. However, it doesn't detail error conditions or specific response format, leaving some gaps in completeness despite the strong annotations and schema coverage.

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 100% schema description coverage, the input schema already documents all parameters thoroughly. The description's 'Args' section largely repeats schema information, though it adds minor context about 'SAME' tracking for sources. This meets the baseline for high schema coverage without adding significant extra meaning.

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 clearly states the specific action ('Create or update a markdown note in the vault'), identifies the resource ('note'), and distinguishes it from siblings like 'save_decision' or 'save_kaizen' by specifying it's for general markdown notes. It goes beyond restating the name by explaining the write-to-disk and indexing behavior.

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 description provides clear context about when to use this tool (for creating/updating markdown notes with optional provenance tracking) and implicitly distinguishes it from read-only siblings like 'get_note' or search tools. However, it doesn't explicitly state when NOT to use it or name specific alternatives among siblings like 'save_decision' for different note types.

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