bw_dtp_get_xml

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

With no annotations provided, the description carries the full disclosure burden and succeeds. It explains side effects (writing a file under the workdir), response shape differences between outputPath and inline modes, the exact file content semantics for the bw_*_get_xml family versus other get tools, and that pagination/projection is skipped so files contain the complete payload. This is unusually rich behavioral detail.

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?

The description is dense and front-loaded with the most important guidance ('ALWAYS prefer outputPath'), and every sentence contributes information. It loses one point because it is a single unbroken paragraph with a long parenthetical about other tools embedded inside the outputPath explanation, which makes it slightly harder to scan.

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 tool with 4 parameters, no annotations, and no output schema, the description covers usage, alternatives, workflow position, file semantics, and response envelopes remarkably well. The only omissions are the meaning of forceCacheUpdate and the exact content of the inline summary envelope, which keeps it from a perfect score.

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 75%, and the description adds substantial meaning beyond the schema for outputPath (workdir-relative path, raw-XML writing behavior, direct reuse as xmlPath, suitability for large responses, pagination skip) and format (default value, effect on inline responses). The only gap is forceCacheUpdate, which has no schema description and is never mentioned in the tool description — an agent cannot infer what it does.

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 states a specific verb ('Get'), a precise resource ('raw DTP XML string'), and the intended purpose ('for PUT updates'). This cleanly separates it from siblings like bw_dtp_details, bw_dtp_get, and the other bw_*_get_xml tools, which are all explicitly differentiated elsewhere in the text.

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 gives explicit, prioritized guidance: 'ALWAYS prefer outputPath', explains exactly when to use inline format='xml' versus format='summary', names the reuse path (xmlPath in bw_dtp_save_and_activate), and contrasts the output with other *_get tools that write JSON rather than raw XML. It even frames the tool as 'Step 1 of read-modify-write', giving workflow context. Nothing is left to inference.

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