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

Annotations only declare readOnlyHint and openWorldHint=false; the description goes well beyond them by stating the exact endpoints used (GET /db and POST /post/TABLE only), the sampling caps for result tables (first 20 nodes/elements, 3 load cases, 2 stage steps) versus whole reads for model tables, the row-count estimate, and the prerequisite that results need an analysed model. This is precisely 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?

A single dense paragraph that front-loads what the tool returns and the result-vs-model-table distinction, then layers constraints. Nearly every clause carries information, though the exporter-preview analogy and parenthetical endpoint list add slight bulk.

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 25 parameters and no output schema, the description does the important work of describing the return shape (rows, headers, sub-tables, POST argument, full-row-count estimate) and the analysed-model prerequisite. Remaining gaps are minor since the schema covers parameter-level semantics at 84%.

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?

Coverage is 84%, so the schema already documents nearly all 25 parameters and the baseline of 3 applies. The description contributes one real behavioral detail not in the schema: when loadCases is omitted, the model's load-case names are also returned via loadCasesInModel. Other parameters (parts, sectionPositions, displacementOption, extraArgument) are left entirely to the schema.

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?

States a specific verb and resource (reads one table from the open CIVIL NX model) and explains the return payload: first rows, unit-labelled headers, sub-tables, and the exact POST /post/TABLE argument. It also distinguishes result tables (sampled) from model tables (read whole), which is genuinely differentiating. It does not name sibling tools such as export_result_tables or civil_read_table, so the agent must infer the preview-vs-export split.

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

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