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

Annotations already declare this a non-read-only, non-destructive, open-world write, and the description adds real behavioral detail beyond them: confirmation is refused while any check is unanswered, acknowledgedIssues must carry the accepted keys, confirming creates the import from confirmed values, and a Corply reviewer still reviews each document. It also addresses idempotency and a confirmation boundary. Some of that (canonicality, generic retry boilerplate) is stock filler, keeping it off a 5.

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 purpose and gating condition are correctly front-loaded, but the body sprawls into instructions for other tools (create_import_intake, uploadUrl, curl -F uploads, add_import_intake_url, read_import_intake loops). Those steps do not belong to this tool's own invocation and push the tool's actual parameter/behavior guidance into the middle of a wall of workflow text.

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?

With no output schema, the description must cover return behavior, and it does signal the post-confirmation state (import created, reviewer step, missing items presented one question at a time). Prerequisites, idempotency, canonicality, and the confirmation boundary are all addressed. Only the unexplained parameters and the lack of any return-shape detail keep it from 5.

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 0%, so the description must carry parameter meaning, and it only partially does. It explains values ('only changed rows, keyed by review row key'), reviewHash, and acknowledgedIssues, but leaves intakeId, requestId, choices, accepted, team, and _corply_context unexplained despite being required or structurally significant. Partial compensation for a nine-parameter schema.

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 opening sentence gives a specific verb and resource: 'Record the founder's confirmation of the reviewed details and import the company from them.' It implicitly distinguishes itself from the upstream siblings (create_import_intake, read_import_intake, add_import_intake_url) by naming them as prior flow steps. It never differentiates from close siblings like confirm_company_import_reading or import_company, so it stops short of a 5.

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?

States the gating condition explicitly: only after the founder chose 'Confirm and import' (or gave corrections), and 'Never confirm without that answer.' It also names the prerequisite flow (create_import_intake → read_import_intake until remaining is 0) and the acknowledgedIssues requirement. It does not contrast this tool with any alternative sibling, so usage is well-bounded but not alternative-aware.

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