Spr analyze drawing

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it explains what is recognised (bends, flange/valve gaps bridged, nozzle stems, reducer/valve labels), the 3D reconstruction convention (X,Y horizontal, Z up, inlet = origin), how attached chat files surface as '[첨부 도면] name path=… candidateId=…', and that ambiguities are surfaced for the user rather than resolved silently.

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 the purpose before diving into ISO/plan mechanics, return contents, attachment encoding, show options and the follow-up call. It is dense and parenthetical-heavy, but nearly every clause carries information; only the trailing '[bulc-mcp rules] DRW-006' pointer reads as boilerplate.

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 correctly carries the return contract ('summary with candidateId, open ends ... runs and ambiguities'), and the re-analysis options are explained in context. The one gap is that no parameter is marked required, so the description should be explicit that a filePath or candidateId (or attachment) must be supplied.

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 already 89%, so the baseline is 3, but the description adds real meaning: the show modes are tied to what the agent will do with them ('lists details (ids, offset, limit, component)'), and it explains where candidateId comes from (earlier analysis or the chat attachment) and why it avoids re-reading. It still doesn't explain entry/rootHint/lineNoPattern beyond what the schema says.

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+resource ('Read a sprinkler / water-spray piping drawing ... recognise a candidate pipe network'), enumerates supported formats (.dxf, .dwg, .pdf, .zip, .png/.jpg) and both projection modes. The sprinkler-piping domain clearly separates it from the sibling arch_analyze_drawing and bulc_drawing_intake, and it names spr_import_network as the downstream consumer.

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?

Gives clear forward workflow ('Then call spr_import_network') and practical routing hints such as 'PDFs with outlined text set needsVision (read the page image instead)' and candidateId re-use 'without re-reading'. It never states when NOT to use it or how it differs from arch_analyze_drawing/bulc_drawing_intake, so explicit alternative selection is missing.

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