Prepare a user-controlled local AI Pack run

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

With no annotations, the description carries the full disclosure burden, and it does meaningful work: it states the tool only returns a plan and that 'Tetrees does not execute client extensions on its hosted servers,' which negates the primary behavioral risk for a prepare-style tool. It does not, however, cover side effects, whether approvedWriteMethods approvals persist, or explain the AVCP audition jargon.

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?

Two sentences, both load-bearing: the first states the deliverable and scope, the second states the non-execution contract. No redundant restatement of the title and no filler, with the most distinguishing fact placed at the end as a deliberate boundary.

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?

The definition is adequate for a moderate-complexity prepare tool: it establishes the plan-not-execute contract and the input constraint. But with no output schema and no annotations, an agent still lacks the plan's format, whether invocation has side effects or creates persisted state, and how this connects to run_ai_pack or execute_client_extension for the actual execution step.

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 50%, so the description must partially compensate. It adds useful semantic context by enumerating what selected extensions reference — 'local skills, MCP tools, resources, prompts, or HTTPS APIs.' It does not illuminate the required task parameter or clarify the relationship between approvedWriteMethods and selectedExtensionIds beyond the schema's own one-line notes.

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 specifies a concrete deliverable — 'a host-readable execution plan' — and a concrete scope: 'connecting this Pack to explicitly selected... local skills, MCP tools, resources, prompts, or HTTPS APIs.' The final sentence clarifies this is a plan-only tool, which differentiates it from execution-oriented siblings like run_ai_pack and execute_client_extension.

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 qualifier 'explicitly selected, Agent-AVCP-auditioned' communicates that the tool is for already-vetted extensions rather than discovery, which gives some usage context. However, no alternative tool is named and no explicit when-not-to-use guidance is provided; the boundary separating this from run_ai_pack or execute_client_extension must be inferred from the italic distinction that Tetrees does not execute client extensions on hosted servers.

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