Execute Archicad API Command

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

Annotations already cover the safety profile (destructiveHint=true, readOnlyHint=false, idempotentHint=false), and the description is consistent with them. The description adds genuine behavioral value beyond annotations: the port prerequisite, the mandatory schema-lookup workflow, and the pagination contract where a 'next_page_token' in the response requires re-invocation with a 'page_token' argument. These are non-obvious runtime behaviors the annotations cannot convey.

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 four sentences are dense but each earns its place: purpose, mandatory prerequisite, port requirement, and pagination handling. The 'CRITICAL WORKFLOW' label adds mild verbosity, but for a destructive generic executor with a prerequisite, emphasizing the workflow is justified. It is front-loaded with the core purpose before the workflow details.

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 complex generic executor with an open-world arguments object and no output schema or parameter descriptions, this description covers the critical workflow: prerequisite schema lookup, port sourcing, and page-token pagination. The main gap is that the response format beyond the 'next_page_token' signal is not described, though the absence of an output schema makes that a moderate rather than severe omission.

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 0% — the schema only provides 'name' as a string and 'arguments' as an unconstrained object with additionalProperties:true. The description compensates substantially: it explains that 'name' identifies the command and that 'arguments' must contain a 'port' key and optionally a 'page_token'. It deliberately defers the full arguments structure to archicad_get_command_schema, which is appropriate for a generic executor, but it does not document all possible argument shapes itself.

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 opens with a specific verb and resource: 'Executes a specific Archicad API command by its name.' This clearly differentiates the tool from siblings (discovery_list_active_archicads discovers, archicad_list_commands lists, archicad_get_command_schema retrieves schemas) because this one is the actual executor. An agent can immediately tell what this tool does and how it differs from the others.

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 provides explicit workflow instructions: it mandates calling archicad_get_command_schema first, requires a 'port' obtained from discovery_list_active_archicads within the arguments, and specifies the pagination loop (call again with a 'page_token' when a 'next_page_token' is returned). This tells the agent exactly when and how to invoke the tool, including prerequisites and the recursive pagination case.

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