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

Annotations already declare destructive=true, but the description adds the traits that matter most here: DRY RUN by default, irreversibility, the skip conditions, and the scope limit ('Only Neuron's copy — nothing is deleted from WhatsApp'). This is exactly the extra context annotations cannot carry.

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?

Five short sentences, front-loaded with the core action and the highest-risk facts (dry run, irreversible). Every sentence earns its place, though the execute/confirmChats sentence is dense and slightly mid-stream.

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?

No output schema exists, and the description references a 'preview' and a 'conversations' number that the agent will need to interpret. It is nearly complete for this destructive, high-stakes tool, though a word on the preview response shape would close the loop.

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 100%, so the baseline is 3, but the description adds the non-obvious coupling between execute and confirmChats (confirmChats must equal the preview's chat count) and the preview-before-execute workflow. That meaning goes beyond the field-level docs.

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 (delete) and resource (messages and their media) plus the crucial nuance that conversations remain empty, which distinguishes it from neuron_delete_message and neuron_clear_media. An agent can tell what this tool does without opening the schema.

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 covers the dry-run default, which chats are skipped (human-handled or flow-blocked), the alternative path (conversationIds vs workspace-wide), and the exact condition for a workspace-wide execute (execute: true plus confirmChats matching the preview count). When-to-use and prerequisites are fully specified.

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