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

Annotations only say readOnlyHint=false / destructiveHint=false; the description adds real context beyond that — it states the call is not purely read-only, that it creates an XBOSS task and persists a processing result, and that each call consumes one token. It also discloses the authentication prerequisite. It is consistent with the annotations, though "institution data changes follow the tool's execution content and existing confirmation procedures" is too vague to be actionable.

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 and the idempotency contract are front-loaded, which is good. But three sentences are spent on idempotency mechanics while the actual selection behavior is one short clause, and phrases like "anonymous taste calls" and the closing Korean boilerplate about institutional changes add noise without meaning.

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, zero-required selection tool with no output schema, the description leaves important gaps: what a selection returns, whether it must follow a search, and how the side effect (task creation / stored result) relates to the original institution data. It compensates well on auth and idempotency but not on the core selection contract.

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 adds substantive meaning the schema defers on: request_idempotency_key's schema text says only "see the tool description," and the description supplies the actual semantics (generate before first request, reuse only to recover a lost response, new key for a new execution, never mutate the provider's own idempotency_key). It also pins account_link_id to the login call. The other eight parameters (row_key, row_index, template_code, etc.) get nothing beyond the schema.

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?

"Select a specific pension premium notice" gives a verb and a resource, but "select" is ambiguous — it never states that the row is identified from a prior list via row_key/row_index, nor what the selection produces (a stored task result?). It also does not distinguish this from sibling retrieval tools such as pension_notification_documents__detail or pension_notices__search.

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 explicitly names the prerequisite (a prior nps_edi__auth__npki_session__login with the same account_link_id) and gives a clear when-to-reuse rule for the idempotency key, which is genuine guidance. However, it never says a prior pension_notices__search is needed to obtain row_key/row_index, and gives no condition distinguishing this from sibling search/detail tools.

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