Install the Tapir add-on

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes far beyond that by disclosing the sha256 verification step, that the default is a no-write dry run, that replacement moves the old copy to a backup folder, that a custom Tapir build loses its own commands when replaced, and the platform-specific permission paths (macOS system password dialog vs. Windows admin-terminal command). These are exactly the consequences an agent needs before agreeing to a destructive write.

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 default behavior and the write trigger are front-loaded, and nearly every clause carries operational weight (verification, backup, platform permissions, restart). It is dense but slightly run-on, packing four distinct concerns into semicolon-chained sentences that could be split for faster scanning.

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?

An output schema exists, so return values need not be described, and the description covers prerequisites, destructive consequences, rollback (backup folder), and platform-specific failure modes. The one small gap is that it does not say how a Windows admin-terminal command result or a dry-run report should be surfaced back to the user, though the output schema likely handles that.

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 0%, so the description must carry all parameter meaning, and it does: 'confirm=true writes' defines confirm, 'archicad_version limits it to one version' defines the scope filter, and 'Never replaces an existing Tapir unless replace_existing=true ... moves the old copy to a backup folder' defines replace_existing including its side effect. All three parameters are covered with semantics the schema cannot express.

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 and resource with the exact artifact version: 'Install the pinned Tapir add-on (2.0.0) into Archicad's Add-Ons folder'. An agent immediately knows this is an installer for a fixed, known payload, not a generic plugin manager, and no sibling tool in the catalog overlaps with it.

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 an explicit safe default ('Dry run by default'), the exact escalation ('confirm=true writes'), an exclusion ('Never replaces an existing Tapir unless replace_existing=true'), a scoping option ('archicad_version limits it to one version'), and prerequisites ('Needs no running Archicad', 'Archicad must be restarted afterwards'). An agent can decide both whether and how to invoke it without guessing.

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