delete_memory

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that deletion is permanent and cascades to vectors and links, which is real value beyond the name. However, it omits permission requirements, behavior when the memory_id does not exist, and idempotency, which matter for an irreversible mutation.

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?

Two short sentences, front-loaded with the destructive action and followed immediately by the safer alternative. Every clause earns its place with no padding.

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?

An output schema exists, so return values need no explanation, and a single-parameter delete is well served by the stated permanence and cascade behavior plus the alternative-route guidance. Only edge-case behavior (missing id, permissions) is left uncovered.

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?

There is one required parameter whose schema description coverage is 0%, so the description should compensate but does not explain what memory_id accepts or how to obtain it. The meaning is largely inferable from the tool name, so this is adequate rather than deficient.

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?

States a specific verb+resource ('delete a memory') and adds the destructive scope ('its vectors/links'), which tells the agent this is a cascading hard delete rather than a soft flag. It also implicitly contrasts with add_memory by recommending correction over deletion. It does not name siblings by name, so it stops short of full differentiation.

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?

Explicitly advises 'Prefer adding a corrected memory over deleting,' which routes the agent to the add_memory alternative and gives a when-not-to-use condition. There is no guidance on confirmation, prerequisites, or when deletion is genuinely the right call, so it is clear but not complete.

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