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

Goes well beyond the destructiveHint annotation by disclosing the blast radius (value removed on every record), irreversibility, and a per-call cost model with a failure exemption. That cost/rollback detail is exactly the kind of context annotations cannot convey.

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 short sentences, zero filler, and the data-loss warning is placed immediately after the action statement rather than buried.

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?

Behavioral and cost context are complete, and annotations already cover the destructive profile, but both parameters remain undocumented in schema and description alike. For an irreversible deletion that gap matters more than for a read tool.

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 mentions either parameter. For a destructive tool, an agent gets no clarification of what 'key' identifies (field key vs. id) or how it relates to the object enum.

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+resource ('Delete a custom field') with scope added: the field and its stored value on every record. That scope separates it from crm_delete_tag / crm_delete_segment / crm_delete_pipeline, though no sibling is named explicitly.

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 destructive nature implies caution, but there is no explicit when-to-use guidance, no pointer to crm_list_fields or crm_define_field as the inspection/creation counterparts, and no statement about prerequisites or how to obtain a valid field key.

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