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

Annotations only give readOnlyHint=false and destructiveHint=true; the description adds real substance beyond that — that a draft return is created on the Wetax side, that a dclr_id comes back and gates subsequent steps, and that unsubmitted returns are purged the next day (important ephemerality warning). It does not address overwrite behavior for an existing draft or whether representative_kind has constrained values.

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 auth prerequisite is front-loaded and each sentence carries information (prerequisite, action, return value, contact shortcut, retention warning). It is bilingual and slightly dense but has no filler sentences.

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 9-parameter mutation with no output schema, the description covers the critical call context: auth prerequisite, the created draft and its identifier, and the next-day deletion of unsubmitted drafts. Gaps are modest — no guidance on re-invocation/overwrite or on error conditions such as a missing or expired session.

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 all nine parameters are already documented in structured form; the baseline applies. The description adds a behavioral note on same_as_member_info (skip sending contact fields) and introduces dclr_id as a return value, but says nothing about jurisdiction_code, representative_kind codes, or required-field combinations.

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 and resource: registers the declarant (representative) and creates an in-progress special-withholding return on Wetax, returning a dclr_id. This distinguishes it reasonably well from submit/review/cancel siblings, though it does not explicitly contrast with the other *_save siblings (target_save, statement_save, adjustment_save).

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?

Explicitly states the prerequisite (prior wetax__session__login with the same account_link_id) and signals sequencing by saying all later steps consume the returned dclr_id, which tells the agent this is an early-stage call. No explicit when-not or naming of the sibling save tools.

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