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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered structurally. The description adds genuinely new behavioral facts beyond that: two server-side guard conditions that cause refusal, which an agent cannot infer from the annotations. It stops short of saying what happens to the field's values or whether the refusal is an error versus a no-op.

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, no filler, with the core action first and the blocking conditions immediately after. Every clause carries information an agent needs before calling.

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?

For a one-parameter destructive tool with full annotations and no output schema, the description covers the main surprise (refusal on in-use and built-in fields). Only a note on irreversibility or the effect on existing template references to the deleted field is missing.

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% and the single parameter is documented as "Smart field id from list_smart_fields." The description adds no further parameter meaning — no format, prefix, or validation detail — so the baseline of 3 applies with the schema doing all the work.

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?

"Remove a custom field from the registry" gives a specific verb (remove) plus resource (custom/smart field) scoped to the registry, which separates it in kind from create_smart_field, update_smart_field and list_smart_fields. It does not explicitly name any sibling or state that update_smart_field is the non-destructive alternative, so it falls short of the full sibling-differentiation bar.

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 supplies concrete usage conditions: the call is refused while any template still references the field, and built-in fields cannot be deleted. That tells an agent both when the call is valid and the two exclusion cases, though it never names what to use instead (e.g. update_smart_field to repurpose, or removing template references first).

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