Save a proven approach so future agents can reuse it and prefer what already worked, reducing repeated trial and error.
Record an approach that worked, so future agents prefer it.
| Name | Required | Description | Default |
|---|---|---|---|
| approach | Yes | The approach that worked |
Changes observed during successful MCP inspections.
v3.1.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Only readOnlyHint=false is annotated, so the description carries most of the behavioral burden; it does add valuable context that the record is meant to shape future agents' preferences. It does not disclose what happens on duplicate or conflicting approaches, whether entries can be overwritten or removed, or what the write returns.
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?
One short sentence with zero filler, and the core action is front-loaded before the rationale clause. Nothing here is wasted or buried.
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 trivial one-parameter write tool with no output schema and minimal annotations, the description covers the essential action and its purpose. It omits how records are scoped, deduplicated, or later surfaced (presumably via get_patterns), which would have made it fully self-contained.
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 a single well-documented parameter, so the baseline is 3. The description restates the parameter's meaning ('an approach that worked') but adds nothing about content expectations, granularity, or how the 2000-character limit should be used.
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?
A specific verb and object ('Record an approach that worked') make the operation unambiguous, and the trailing clause explains its downstream effect. It does not, however, distinguish itself from close siblings like save_failure or save_context, so an agent must infer the boundary from the name alone.
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 phrase 'an approach that worked' implies the trigger condition for calling it, but there is no explicit guidance on when to prefer this over save_context, save_summary, or save_failure, and no exclusions or prerequisites. Usage is inferable rather than stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.