delete_records

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

Annotations already declare destructiveHint=true, but the description adds substantial context they cannot: the cascading deletes NX performs (load case loads, combination entries, nodal loads, supports, masses, beam loads, end releases, pressure loads), the 50-id cap, and post-conditions where /DESIGN tables may reset to defaults or remain unchanged. This is exactly the disclosure an agent needs before a destructive call.

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?

Purpose and the two-step protocol are front-loaded, then constraints, then side effects, then result semantics. Dense but every sentence carries operational information; the parenthetical explanations of why records are refused earn their space.

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?

With no output schema, the description usefully explains what the result reports (which records were reset, unchanged, or removed from other tables). The main omission is how to obtain and pass confirm_token, which is central to a two-step destructive flow.

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%, so the description must carry parameter meaning; it does well for ids (listed ids only, one DELETE per id, max 50) and table (a single /db or /DESIGN table). It says nothing about confirm_token, whose presence drives the preview/apply protocol, and nothing about product (gen vs civil).

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?

Opens with a specific verb and resource plus hard scope: 'Delete records by id from one /db or /DESIGN table,' and immediately bounds it ('one DELETE per id; there is no way to empty a table here'). It does not name a sibling such as write_records to contrast with, so differentiation is left implicit, but the operation is unmistakable.

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?

'Two steps: preview, then apply' gives a clear call sequence, and the refusal rules (nodes used by elements, used materials/sections/thicknesses) tell the agent what preconditions must hold. The gap is that the preview and apply steps are never tied to the confirm_token parameter, and no alternative tool is named for cases where deletion is refused.

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