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

Annotations already declare readOnly, idempotent, and non-destructive, so safety is covered. The description adds genuinely useful behavior beyond that: the fact that a part's analysis can be 'pending' and that the call can optionally block server-side for it.

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, no filler; the return contents are front-loaded and the optional wait behavior follows. Slightly dense enumeration in sentence one, but every item earns its place.

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?

Return values are already covered by an output schema, and both parameters are fully documented in the schema; the description still summarizes the payload and the pending/wait nuance. For a 2-parameter read tool, nothing needed to call it correctly is missing.

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 the baseline is 3. The description earns the bump by explaining why wait_seconds exists (to wait on a pending part 'instead of polling'), which the schema only describes mechanically as '0 answers at once'.

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 resource (part) and enumerates exactly what is returned: status, measured geometry in mm, suggested units, DFM warnings, and fitting processes. That is far more concrete than a generic 'get_part', though it never names a sibling to contrast against.

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?

Gives a clear usage instruction for the pending-analysis case: pass wait_seconds to block in this call 'instead of polling'. It does not say when this tool should be skipped or which sibling to prefer, but the polling-vs-wait tradeoff is explicit.

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