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

With readOnlyHint=false and destructiveHint=false already declared, the description adds real context beyond annotations: the auth dependency, the full idempotency-key lifecycle (generate before first request, reuse for recovery only), and the cost disclosure '호출마다 토큰 1소진.' It does not describe server-side effects of 'prepare' – whether anything is persisted – which is the main remaining gap.

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 prerequisite is correctly front-loaded, but the idempotency paragraph is long and bleeds into irrelevant material: 'This optional key is not available to anonymous taste calls' is garbled, and the warning about provider-specific idempotency_key fields does not map to any parameter here. Signal survives, but filler could be cut.

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?

Nine optional parameters, no output schema, and only minimal annotations mean the description carries weight. It covers auth, idempotency, and cost well but says nothing about what the tool returns or how the row_key / row_index / template_code combination selects a result – details an agent must infer from the schema alone.

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 baseline is 3, but the description earns above that by fully explaining request_idempotency_key, whose schema entry only defers with 'see the tool description.' It also clarifies that a provider-specific idempotency_key is a different field, preventing a likely mix-up.

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 says it will 'prepare the print and save parameters for one certificate result,' which is a concrete verb+resource, but it never reconciles this with the tool name 'document_view' – an agent cannot tell whether the tool returns a document, a URL, or just argument scaffolding. It also never names the sibling (nps_edi__b1__certificates__application_results__search) that supplies the row identity, leaving the pairing implicit.

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 states a hard prerequisite ('REQUIRES prior nps_edi__auth__npki_session__login call with same account_link_id') and gives precise guidance for the idempotency key: reuse only to recover a lost response, new key for a new execution. What's missing is guidance on when to prefer this over the sibling search tool or what qualifies as a valid 'one certificate result.'

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