Tendon geometry and prestress / 钢束几何与预应力

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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description goes well beyond them: it states no backup/rollback/analysis is performed, that writes refresh the model, that returns are requested names/load summaries rather than verified coordinates or effective prestress, that reusing a tendon name can replace complete geometry, and that load assignment is not a promise of idempotency, with a read-back-before-retry instruction. 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?

Front-loaded with purpose, then operations, then caveats, which is the right order for a five-branch dispatcher, and each sentence carries information. It is nonetheless long and repeats the destructive/name-reuse warning across the top-level description and the nested branch descriptions, costing a little density.

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 multi-operation destructive write tool with an output schema, the description supplies everything an agent needs: branch selection, prerequisite ordering (material → property → geometry → element assignment → load), the fact that no analysis or rollback occurs, and the follow-up activation/analysis path. Return-value details are covered by the output schema, so nothing material 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% (baseline 3), and the description still adds cross-parameter semantics the schema states only in fragments: position_type flips point_insert from coordinates to [end, direction, element_id], num counts tendons rather than control points, apply_prestress accepts one name or a list, tension_type selects start/end/both, and force is forwarded without unit conversion against a verified export. These interactions materially improve correct invocation.

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?

The opening sentence names the specific verb+resource (define named tendon paths and apply prestressing loads), and the bulleted list enumerates each of the five operations with a distinct verb (defines, places, matches, targets). It explicitly separates itself from edit_loads, manage_checks, query_model and query_results, so an agent can route 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?

Explicit when-to-use rules are given per operation (create_tendon_property for mechanical/loss params, create_tendon_2d for planar profiles, add_tendon_3d for spatial paths, assign_tendon_elements to match elements, apply_prestress to target existing names in an existing load case), plus named alternatives for adjacent concerns (edit_loads, manage_checks, query_model, query_results) and a stated workflow order ending in edit_construction and analyze_model.

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