memory_delete

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

With no annotations present, the description carries the full behavioral transparency burden. It clearly discloses the destructive nature, idempotency, the '0 deleted if no match' behavior, the no-op for no args, and the explicit guarantee that a full-table delete is impossible. It could add permission or side-effect details, but the core behavioral profile is 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 description is compact and front-loaded, with the core action stated first. Every sentence adds distinct value: mode selection, return value, idempotency, and safety no-op. There is no filler or redundancy.

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 3-parameter destructive tool with no annotations and no output schema, the description is remarkably complete. It covers all invocation modes, precedence, return information, idempotency, and the most dangerous edge case (accidental full deletion). Nothing essential for an agent to call the tool correctly is missing.

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 input schema already provides 100% parameter documentation, so the baseline is 3. The description adds valuable semantics beyond the schema by explaining the mutual-exclusion priority relationship among id, category, and category_prefix, and by giving a concrete batch prefix example. This extra context meaningfully improves the agent's ability to choose parameters correctly.

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 and direct object ('Delete memories from the vector store'), making the tool's core function unmistakable. It then enumerates the three modes, which distinguishes it cleanly from sibling memory tools like memory_add, memory_search, and memory_stats by showing exactly what this tool does differently.

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 gives strong usage guidance for when to use each mode: single row by id, exact category, or category prefix for batch cleanup, with examples like 'test:'. It also states the priority order and the no-op safety behavior. It does not explicitly contrast with alternative sibling tools, but there is no overlapping delete tool among the siblings, so the guidance is sufficient.

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