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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety needs no elaboration. The description adds genuinely non-obvious behavior: the advisor may ask up to 2 clarifying questions, implying a multi-turn flow that the agent must handle by returning with `answers` — context an agent could not get from annotations or schema.

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 with no filler. The core action and its output are front-loaded, and the input-mode constraint follows immediately after, so an agent reads the essential facts in the first pass.

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 29-parameter tool with no output schema, the description still communicates what comes back (process, material, color, strength) and how the interaction may loop, which is the critical missing context. The remaining gap is that it does not indicate what the response looks like structurally when answers are needed versus when a recommendation is returned.

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 100%, so every parameter is already documented and the baseline is 3. The description does add structural meaning by framing the two input families (path vs. template+sizes) and by explaining that earlier Q&A is passed back, but it does not clarify how the template-scoped parameters group together beyond what per-property descriptions already say.

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 ("Run ply's material advisor for a part") and names the concrete output of the tool: a recommended process, material, color and strength. It also anchors the tool to a known surface ("Help me choose" on plyparts.com), which clearly separates it from siblings like list_materials or price_file.

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 distinguishes the two valid invocation modes — a file `path` or a template plus sizes for a built part — which effectively says when each input shape applies. However, it never says when to prefer this tool over alternatives such as list_materials or make_part, so routing between siblings is left to inference.

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