Store a Memory

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

Annotations indicate a non-read-only, non-idempotent operation. The description supplements this with key behavioral context: the merge/replace strategy to avoid duplicates, the cross-model persistence purpose, and specific error messages. It does not contradict annotations, but could more explicitly state the risk of duplicates if recall is skipped, so it falls short of a 5.

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 well-structured with clear sections: IMPORTANT note, usage instructions, content requirements, args summary, return value, and error handling. However, it is somewhat lengthy and partially redundant with the schema descriptions (e.g., listing args again). The front-loading of the 'IMPORTANT' directive is effective, but a more streamlined version would earn a 5.

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 tool with no output schema and six parameters, the description is exceptionally complete. It covers the full workflow: when to use FlowMCP, the recall-first precondition, merge/replace strategy, alternative project-specific tool, detailed parameter requirements, expected return (ID and title), and error scenarios. An agent can confidently invoke this tool correctly without ambiguity.

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?

The schema covers all six parameters with detailed descriptions, so baseline is 3. The description adds value beyond the schema by emphasizing title specificity (e.g., not "user project"), content depth ('Write the content as if a completely different AI model needs to read it'), and explaining the category enum usage. It also connects validation errors to parameter constraints, enriching semantic understanding.

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 an explicit statement of purpose: 'Store a new memory in FlowMCP for cross-model persistence.' It also distinguishes itself from siblings by instructing to use flowmcp_recall for checking existing memories and flowmcp_project for project-specific context, making its scope clear.

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 explicit when-to-use guidance: 'Always check FlowMCP when the user asks about projects, technical details, or previous work.' It mandates a precondition: 'ALWAYS call flowmcp_recall first to check if a similar memory already exists.' It also names an alternative: 'prefer using flowmcp_project with action='update_section' for project-specific context.' This goes beyond typical usage guidance.

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