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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false. The description adds real value beyond that: the blank workspace is temporary and gets removed if the founder switches away, naming it preserves the draft, and the requestId is a fresh UUID reused on retries. The trailing boilerplate (canonicality/retry/confirmation) is generic template text and even says 'this read', which muddies rather than clarifies the write nature.

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 first three sentences are well front-loaded and useful, but the trailing Canonicality/Idempotency/Confirmation-boundary block reads like reusable cross-tool boilerplate that adds little for this specific call. Roughly half the text does not earn 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?

For a create-style tool with no output schema and 0% schema coverage, the description covers alternatives, transience, idempotency and prerequisites adequately, but leaves the _corply_context parameter and the returned draft identity unaddressed.

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 0%, so the description carries the burden. It does explain requestId semantics (fresh UUID, reused on retries) and implies the name parameter preserves the draft, but the nested _corply_context object (id/receipt) is never mentioned, leaving one of three parameters undocumented.

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+resource (start a new-company draft workspace) and explicitly scopes it: for founders who want to begin before choosing a name. It also distinguishes itself from save_application (named incorporation) and import_company (existing legal company), so an agent can route without opening sibling schemas.

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 the selecting condition ('wants to begin before choosing a name') and names two concrete alternatives with their own conditions (save_application with newCompanyRequestId for named incorporation; import_company for an existing legal company). The prerequisite statement is also called out.

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