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

Annotations already declare readOnlyHint/idempotent/destructive=false, so safety is covered, yet the description adds meaningful context: no tax facts are sent, no return is written, PII (SSN/ITIN/PIN) is deliberately absent and typed by the taxpayer, placeholders are refused by path until replaced, and unknown arguments are rejected by name. These are error-behavior and data-handling facts not derivable from the annotations or schema.

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?

Almost every clause carries information, so there is little padding, but the text is a single sprawling construction stitched together with colons and parentheses, which makes the three modes hard to scan. It is front-loaded only weakly, starting with continuationHandle rather than the purpose or the mode switch.

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 an output schema present, return values need not be described, yet the description covers them plus PII handling, placeholder refusal, tax-year location, and rejection of extraneous arguments. The mutual exclusivity of the three modes is enforced by the oneOf schema but only implied in prose, which is the one small gap.

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?

With 75% schema coverage the baseline is 3, and the description goes beyond it by explaining what each mode returns (outline shape {"x-section":"<name>"}, section-level sha256, presets and askTheTaxpayer messages, REPLACE_WITH_TAXPAYER_VALUE refusal semantics). It adds little about continuationHandle itself beyond naming it as the filing session handle, which keeps it below a 5.

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 uses a specific verb and resource ('Returns the packet schema a completed return packet is checked against') and enumerates the three retrieval modes, so an agent knows exactly what it gets. It does not distinguish itself from the siblings (create_filing_session, continue_filing_session), though their names suggest session mutation versus schema retrieval, making confusion unlikely.

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?

Mode selection is spelled out: requestPacketSchema=true for the digest/outline/section list, packetSchemaSection=<name> for one section, packetStarterTemplate=<id> for one starter packet. It also states what is not accepted ('any other argument is refused by name' and the tax year is not a tool argument), covering the when-not side. There is no explicit comparison to alternatives, but no real alternative exists among the siblings.

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