archicad_check_model

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered structurally. The description adds the substantive behavioral content of what is inspected, but says nothing about result shape, whether findings are truncated, or that maxPerCheck caps output. With annotations doing the safety work, a 3 reflects real but incomplete added context.

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 front-loaded sentence that opens with the tool's purpose and lists checks efficiently, with zero padding. It is dense rather than verbose, though the comma-list format reads more like a spec than a prompt-facing cue.

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 zero-required-parameter, read-only tool with no output schema, the definition covers the 'what is checked' dimension adequately but omits return format and the meaning of maxPerCheck/selectedOnly scoping. An agent knows what it validates but not what it gets back or how results are bounded.

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 80% and the checks enum is exhaustively documented in the schema itself, including what each check means. The description adds no parameter-level guidance of its own, so the baseline of 3 for high coverage applies.

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 description names a specific resource (model quality checks) and enumerates exactly what is inspected: missing/duplicate IDs, unclassified elements, duplicate geometry, hidden/locked layers, zero-area zones, unnamed/empty stories. An agent can tell this is a read-only validation tool and distinguish it from the many creation/mutation siblings (CreateWalls, MoveElements, classify_elements). It is a noun-phrase enumeration rather than an explicit verb, which keeps it just short of 5.

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?

There is no statement of when to reach for this tool versus alternatives such as archicad_model_summary, archicad_quantities, or the individual GetElements/FilterElements tools. The only usage signal is the implied 'use it to audit model hygiene', inferred from the check names. No exclusions or prerequisites are given.

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