demonstration_plan

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description explains that even in read_write mode the tool itself does not execute writes—the plan contains paired create/delete steps. It also discloses that the plan reports refused steps, coverage gaps, and excluded tools. No contradiction with annotations.

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?

Although long, the description is tightly organized with clear sections, bolded mode names, and bullet points. Every sentence adds necessary operational detail—execution order, coverage reporting, exclusions, final reporting, and the learner-account caution. Nothing is redundant.

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 tool of this complexity, the description covers purpose, mode semantics, execution instructions, reporting expectations, and safety constraints. The presence of an output schema means the return format need not be described in prose. The warning about tens of thousands of real people is a critical real-world detail.

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?

The schema only shows mode with a default and no enum. The description fully defines both values: 'read_only changes nothing' and 'read_write also creates and deletes CONTENT', plus cleanup pairing. This is exactly the meaning an agent needs and goes well beyond the bare schema.

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 states precisely what the tool does: 'Return an ordered plan for demonstrating this server' and clarifies the plan is executed by the agent, not the tool. It distinguishes this meta-tool from the many sibling CRUD and read tools by explaining it returns steps rather than performing operations.

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 gives explicit instructions on how to use the plan: 'Call the tools it names, in order, substituting ids from earlier steps where a placeholder says so.' It also details mode-specific behavior, what the plan reports, and how to report results at the end. The warning about learner steps provides concrete guidance on what not to do.

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