memory_delete

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

With no annotations, the description correctly carries the full burden: it discloses that the destructive action is recoverable, records an audit tombstone, and refuses MEMORY.md. This goes beyond a generic 'delete' statement, though it omits edge behavior for nonexistent files or non-.md paths.

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?

A single sentence packs action, mechanism, recoverability, audit side effect, and a safety restriction; the bilingual version is still compact and front-loaded. No filler or repetition of schema details.

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 destructive tool with no annotations and no output schema, it provides enough core context: target scope (.md), recovery trail, audit effect, and the protected file. It lacks explicit return/error behavior or what happens if the path does not exist, but these are minor for a simple delete operation.

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 67%; path and summary are already described in the schema. The description adds no new meaning to the parameters and does not clarify the agent parameter, but the parameter names and defaults make it usable.

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 names a specific action—deleting a .md file—and the mechanism (move to .trash/, recoverable) plus the audit tombstone. It clearly differentiates from sibling tools like memory_update/memory_write as a deletion operation. The explicit refusal of MEMORY.md adds precision.

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?

Usage is implied by 'delete a .md file' and the sibling set; no explicit when-to-use vs memory_update or when not to beyond MEMORY.md. It states the restriction on MEMORY.md but does not describe alternatives for cases like renaming or editing.

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