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

Beyond the destructiveHint=true annotation, the description discloses the WRITE_CONFIRMATION_REQUIRED preview protocol, 10-minute single-use token semantics, argument-change invalidation, quota consumption ('호출마다 토큰 1소진'), 15-minute download URLs, 7-day file retention, and the anonymous recovery_receipt's irrecoverable loss and non-publishability. These are substantive behavioral facts the annotations could not convey, and nothing contradicts readOnlyHint=false/destructiveHint=true.

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 critical prerequisite and write-confirmation flow are front-loaded, but the body is a single dense paragraph that jumps between preview flow, file retention, anonymous recovery receipts, and quota notes with no grouping. The lengthy recovery_receipt boilerplate is generic result-handling text that competes with the issuance-specific instructions an agent needs first.

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 10-parameter, nested-object, no-output-schema write tool, the description covers preconditions, the confirmation protocol, what the call returns, file artifact retention and refresh paths, and receipt handling. An agent has everything needed to invoke it correctly and safely.

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 100%, so every parameter (phone, business_address, receive_method, certificate_purpose, confirmation_token, account_link_id, pre_consent) is already documented in the schema. The description adds only relational context — same account_link_id as the login, pre_consent must be true, token reuse rules — which is marginal beyond the schema, so the baseline 3 applies.

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 makes clear this performs an issuance that 'writes to the institution' and ultimately 'Returns a download link for the issued certificate', matching the title's certificate-issuance intent. It does not however explicitly differentiate this from the sibling gov24__business_registration_certificate__issue or the many hometax/other certificate-issuance tools, so the agent must use the name/title to disambiguate.

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?

It names the prerequisite (prior gov24__session__login with the same account_link_id), spells out the mandatory two-step flow (preview first, confirm only after the user agrees), states exclusions such as never sending the token without user consent and that changing any argument invalidates the token, and routes expired links to xdata__job__result. This is explicit when-to-use guidance plus a named alternative for the recovery case.

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