delete_all_memories

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

With no annotations provided, the description carries full burden. It discloses the destructive behavior ('Delete every memory') and clarifies that entities are preserved, but lacks critical details like whether this is irreversible, requires specific permissions, has rate limits, or returns confirmation data. For a mass-deletion tool with zero annotation coverage, this is insufficient.

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 a single, efficient sentence that front-loads the core action ('Delete every memory'), specifies the scope, and adds a crucial qualifier ('but keep the entity'). Every word earns its place with zero 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?

Given the tool's high complexity (mass deletion with 4 parameters) and lack of annotations, the description is incomplete despite having an output schema. It covers the basic purpose and scope but misses behavioral risks, permission requirements, and confirmation details that are critical for safe invocation. The output schema may help, but the description itself doesn't adequately prepare the agent.

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 description coverage is 100%, with each parameter well-documented in the schema. The description adds minimal value beyond the schema by implying these parameters define the deletion scope, but doesn't provide additional semantics like interaction effects between parameters or default behavior specifics. Baseline 3 is appropriate given high schema coverage.

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 the specific action ('Delete every memory') and resource ('in the given user/agent/app/run'), with explicit differentiation from siblings like delete_memory (singular) and delete_entities (different resource). The qualifier 'but keep the entity' further distinguishes it from delete_entities.

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 implies usage context by specifying scope parameters (user/agent/app/run) but doesn't explicitly state when to use this tool versus alternatives like delete_memory (for single deletions) or delete_entities (for deleting entities, not memories). No explicit exclusions or prerequisites are mentioned.

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