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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds a genuinely useful nuance: stored values are not erased, they simply stop being shown on conversations/contacts. That distinction matters for a destructive call and is not derivable from the annotations.

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, action first, consequence second. No filler and nothing to trim.

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?

Adequate for a single-parameter destructive delete whose safety profile is already carried by annotations, and no output schema exists to explain. Still missing the permanence/reversibility question and how to identify the target attribute, which the 0%-coverage schema leaves entirely open.

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 0% and the description never references attribute_id — no hint on where to obtain the ID (e.g., list_custom_attributes or get_details_of_a_single_custom_attribute) or what an invalid ID yields. With one undocumented parameter, the description fails to compensate for the schema gap.

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?

Specific verb ('Delete') plus resource ('custom attribute') in the first sentence, which cleanly separates it from the sibling create_custom_attribute, update_custom_attribute, and list_custom_attributes. An agent can identify the operation 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?

No when-to-use guidance, no prerequisites (e.g., required permissions or that the attribute must exist), and no mention of update_custom_attribute as the non-destructive alternative. The consequence sentence hints at impact but does not route the agent.

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