Arch analyze drawing

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

Annotations already declare read-only/idempotent/non-destructive/non-open-world, so the safety profile is covered. The description adds meaningful behavior beyond that: the file is read on this PC only (local, no uploads), the needsVision fallback for rasters/outlined PDFs, and the returned artifacts (candidateId, summary, questions DRW-001…003). It stops short of describing pagination limits on show output beyond the schema's limit description.

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 core verb and resource, then progressively narrower detail (formats → extraction list → return artifacts → fallback → show values → read-only). It is dense and readable, though the single run-on sentence packs a lot, and the bracketed 'bulc-mcp rules' fragment is terse enough to be ambiguous about its purpose.

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?

No output schema exists, so the description carries the return-value burden — and it does, naming candidateId, summary, and confirmation questions (DRW-001…003). With 7 parameters including a nested options object, some option semantics rely on the schema, but the tool's overall contract is sufficiently complete for correct invocation.

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 57%, so the schema documents roughly half the params. The description adds some value: it enumerates show values (walls | openings | columns | rooms | levels | layers) and mentions layer-role and scale inputs conceptually. But it does not clarify ids, or most nested options (wallThicknessRange, minWallLength, page) beyond what the schema already states, leaving the undocumented half partially unexplained.

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 (Read/recognise) and resource (architectural floor plan) with a precise enumeration of what is extracted: units/scale, layer roles, wall centrelines, doors, windows, columns, stairs, rooms. It distinguishes itself from the sibling spr_analyze_drawing (sprinkler) and names arch_import_floorplan_report as the downstream step, so an agent can place it without opening other schemas.

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 usage context: use it for .dxf/.dwg/.pdf/image plans, and explicitly routes the agent when images/outlined PDFs return needsVision — 'read the picture yourself and call arch_import_floorplan_report.' It also notes the re-analysis path via candidateId. It does not spell out when NOT to use it vs. other intake tools, so it falls short of a full 5.

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