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

Annotations only declare readOnlyHint=false / destructiveHint=false. The description adds real depth beyond that: secrets are never accepted as MCP inputs (auth model), each call consumes one token (cost), and a detailed idempotency contract for retry vs. new execution. That is exactly the kind of context annotations cannot carry.

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?

Purpose and the 'call FIRST' rule are front-loaded, and every sentence carries information. The idempotency block is dense and the trailing Korean token-cost note is a bit tacked on, but nothing is filler.

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 2-parameter session-init tool with full schema coverage and no output schema, the description covers purpose, ordering, auth, cost, and retry semantics. Remaining gaps (session lifetime, behavior when a session is already active) are modest.

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 the baseline is 3; however, the schema's own request_idempotency_key description just points back to the tool description, which then supplies the actual reuse/new-key semantics. account_link_id auto-resolution is covered by the schema. The description meaningfully extends the idempotency parameter.

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: 'Create a Woori Bank speed-account inquiry session from an existing account link.' Combined with the provider prefix, an agent can tell this apart from other session/login siblings (hana, kb, shinhan, etc.) without opening any schema.

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 an explicit prerequisite ordering rule. It doesn't articulate the inverse case (what to do if a session already exists, or how it expires), so it stops short of full when/when-not guidance.

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