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

Annotations declare destructiveHint=true, and the description aligns by stating it 'saves' information, implying a write operation. The description adds valuable behavioral context beyond annotations: the conversational collection flow, the no_ssn skip path, and the paper-filing delay consequence. It doesn't explicitly state whether the operation is reversible or what happens on overwrite, but the destructive hint plus the detailed workflow is strong. No contradiction with annotations.

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 description is three sentences and front-loads the core purpose and the most important conditional (SSN/ITIN question). Every sentence earns its place: purpose, conditional workflow, and field list. Slightly dense but appropriately sized for a complex multi-field collection tool.

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 tool's complexity (4 params, nested objects, output schema present), the description covers the essential workflow and field list. It doesn't explain the output schema or return value, but the presence of an output schema reduces that burden. It also doesn't mention submittedVia or submittedAt semantics, but those are likely internal metadata. Overall, an agent has enough to invoke it correctly.

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 only 25%, so the description must compensate. It does: it enumerates the fields to collect conversationally (date of birth, employee counts, first wages date, closing month, reason for applying, prior EIN, principal business activity) and explains the no_ssn/ssnItin decision. It doesn't map every schema field (e.g., submittedAt, submittedVia, employeesHousehold/Agricultural/Other are partially covered by 'employee counts'), but it adds meaning beyond the raw schema for the key parameters.

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 description clearly states the tool's purpose: it collects and saves EIN (SS-4) filing information after the company is filed with the state. It uses a specific verb ('collects and saves') and identifies the resource (EIN filing info), distinguishing it from sibling tools like formation_get_ein_filing_info (which retrieves) and itin_submit_itin_intake (which handles ITIN applications).

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 provides explicit when-to-use guidance: it should be used after the company is filed with the state. It also gives a clear conditional workflow: first ask whether the user has an SSN or ITIN; if not, set no_ssn and skip it, with a consequence (paper filing takes ~45 business days). This is actionable and leaves little to inference.

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