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

The description adds side-effect information beyond the annotations: it uses one token per call, creates an XBOSS job and stores the processing result, and explicitly states that the call is not purely read-only, which is consistent with readOnlyHint=false. The idempotency semantics also tell the agent how to recover from a lost response. The confusing phrase 'anonymous taste calls' undercuts it, and the description still does not say how session state is persisted.

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 first sentence is correctly front-loaded with the critical directive, but the body blends English and Korean, runs the idempotency rules together, and closes with generic boilerplate about how provider data changes follow per-tool procedures. Several clauses ('without it, calling again remains a new request') restate earlier points and could be compressed.

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 three-parameter login tool with annotations and no output schema, the definition covers triggering and idempotency well, but says nothing about what a successful login yields (session handle, expiry, subsequent behavior) or how failures such as an invalid certificate surface. Missing the pointer to session-status as the way to verify an existing session also leaves a gap for an agent that must establish auth before the sibling EDI tools.

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 already 100%, so the baseline is 3. The description still adds real meaning for request_idempotency_key: when to generate it, when to reuse it with identical arguments, when to mint a new one, that it is unavailable to anonymous calls, and that it must not be confused with a provider-specific idempotency_key. The other two parameters are left entirely to 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?

States a specific action, 'Login to NPS EDI via NPKI certificate', with a named mechanism (NPKI certificate) and an explicit scope qualifier, 'for this provider', which separates it from the other providers' login siblings in the catalog. It does not, however, distinguish itself in text from the same provider's session-status or other auth siblings.

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?

'Call this FIRST before any other tool for this provider' gives a clear ordering rule that an agent can act on, and the idempotency paragraph gives concrete when-to-reuse guidance for the key. What is missing is the inverse case: it never says what to do if a session already exists (for example, check nps_edi__auth__session__status) or when not to call this.

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