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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses the escalation flow: unapproved payments are parked with ESCALATION_REQUIRED and execute on retry with the same idempotency_key. It also states the credential never reaches the agent, which is real auth context. It stops short of saying what state a parked/mutated resource leaves behind, but the disclosure is well above the annotation baseline.

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?

Three tightly packed sentences with zero filler, front-loading the operation and endpoint before the escalation semantics. Slightly dense in the second sentence but every clause earns its place.

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 7-parameter write tool with no output schema, the description covers the critical behavioral surfaces: spend gating, pre-approval parking, retry idempotency, and credential isolation. It omits what a successful response returns and which sibling to poll for approval status, so it is strong but not fully closed.

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 86%, so the schema already documents body, path, facts, intent, method, user_token, and idempotency_key. The description reinforces only the idempotency_key retry semantics, which the schema also states, adding no new per-parameter meaning. Baseline 3 is appropriate where the schema does the heavy lifting.

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 states concrete verbs (create, change, pay) and the exact target endpoint (frankfurter.dev/v1/latest), with the HTTP methods enumerated. The opaque tool name and URL-as-resource mean an agent must read the description to know what is being written to, but the write/read split against lst-637408c1b10f_read is inferable from the '· write' title. Clear purpose, though not differentiated from money-flow siblings like pay.

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?

Usage is implied through the gated-decision/spend-limit framing, which tells the agent this is the write path for a spend-controlled API. However, it never says when to prefer this over sibling write tools such as pay, stripe_demo, or lst-a23997bcffc7, nor when to consult approval_status. The alternative-selection guidance is left to inference.

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