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

Adds value beyond annotations: pinned entries never forgotten, dry_run safety, auth requirements. Annotations (destructiveHint=true) consistent, no contradictions.

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?

Three dense sentences, each purposeful. No wasted words, front-loaded with purpose.

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?

Covers main points: action, safety, pinned, auth, filters. Lacks explicit return format beyond dry_run, but acceptable given no output schema.

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?

Clarifies dry_run behavior (lists candidates), imposes filter requirement beyond schema (schema only requires handle). Improves understanding of optional filter params.

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?

Description clearly states 'Delete memory entries matching filters', specifying verb (delete) and resource (memory entries). It distinguishes from siblings like store_memory or recall_memories by focusing on deletion and requiring filters.

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?

Provides context: dry_run safe, at least one filter required, owner-only auth. Does not explicitly name alternatives but implies when not to use (e.g., when wanting to update or store).

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