Delete a Memory

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

Annotations already declare destructiveHint=true, but the description adds the explicit irreversible nature ('This cannot be undone') and specifies the exact effect ('Permanently delete a memory'). It also discloses the return value ('Confirmation of deletion'), which is useful since there is no output schema. The long preamble about FlowMCP's general purpose is not tool-specific, but the core behavioral facts are well covered.

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 core delete instruction is concise, but the description includes a two-sentence preamble about FlowMCP's broader capabilities that is not specific to this tool. The Args/Returns structure is clear and front-loaded with the most critical warning, yet the preamble feels extraneous for a simple delete operation. The description earns a middle score for being organized but not tightly focused.

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 single-parameter destructive tool with strong annotations and no output schema, this description is complete. It covers the purpose, irreversibility, usage conditions, parameter source, and return value. The context signals confirm the schema is fully documented, so the description fills the remaining gaps effectively.

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% for the single parameter, so the schema already documents the memory_id field. The description repeats the instruction to get the ID from flowmcp_recall results, which matches the schema description. Since the description adds no new semantic details beyond the schema, a baseline score of 3 is appropriate.

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 'Permanently delete a memory' with a specific verb and resource. It also explicitly notes irreversibility ('This cannot be undone'), which differentiates it from sibling tools that handle storing, recalling, or pushing memories. No ambiguity about the tool's function.

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 usage boundaries: 'Only use when the user explicitly asks to remove a memory, or when a memory is clearly outdated and no longer relevant.' It also indirectly references the retrieval workflow by instructing to get the memory_id from flowmcp_recall results, which is the appropriate companion tool. This gives clear when-to-use guidance.

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