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

Annotations already mark readOnly, idempotent, and non-destructive. The description adds that it 'calls no model, costs nothing, and never runs out of quota,' providing cost and reliability context not present in annotations. It also discloses the output includes example calls and recipes, giving behavioral insight.

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?

Three sentences effectively front-load the core function, then add use-case examples and cost guarantees. No wasted words; each sentence adds distinct value.

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 description is fully self-contained for a discovery tool: it explains the return value (tools, examples, recipes), when to use it, and its operational constraints (deterministic, no cost). An output schema exists, so return details are covered elsewhere.

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 already provides a full description of the 'task' parameter with examples, so the description adds little new parameter-specific meaning. It reiterates 'plain language' and 'any language,' which is mildly redundant. Baseline 3 is appropriate.

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 clearly states the tool maps a plain-language task to the exact tools on the server with example calls, distinguishing it from sibling task-specific tools like make_chart or render_diagram. The title 'Find the right tool for a task' reinforces this discovery role.

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?

Explicit guidance 'Call this FIRST when you are not sure what this server offers' tells the agent when to invoke it, and the contrast to 'reading the whole catalogue and guessing' provides a clear alternative. The mention of multi-step recipes also covers cases requiring chaining.

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