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

Annotations already declare read-only, non-destructive, closed-world. The description adds legacy gating, brand exception, and internal-only status, which are valuable behavioral constraints beyond annotations. It does not detail return format or polling behavior, but with annotations covering safety this is strong.

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 critical warning is front-loaded, but the description repeats the create-design availability rule and ends with the actual purpose ('Internal tool for widget UI polling') rather than leading with it. 'All instructions below' is inaccurate since only one sentence follows. Adequate but could be tighter.

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?

Given the routing complexity, the description covers when to use, when not to use, the brand exception, and the failed-call caveat. It lacks return-value detail, but for a polling tool with no output schema the routing completeness is the priority, and it largely delivers.

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 coverage is 100%, so both parameters are fully documented in the schema. The description adds no parameter meaning beyond 'Poll that job' and does not mention user_intent. Baseline 3 is correct when the schema does the heavy lifting.

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 it is a legacy-only internal polling tool and distinguishes from create-design and get-create-design-async-job. However the core resource is never named: it does not say it retrieves design candidates or what a 'design candidate' is, so the agent must infer from the tool name.

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 when-not: do not call when create-design is available; call get-create-design-async-job instead. Gives the brand exception and clarifies that a failed create-design call does not make it unavailable. Very strong routing guidance.

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