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

Beyond the readOnlyHint/idempotentHint annotations, the description discloses that results are masked references that never include account or routing numbers, and that each carries readiness plus the next human step. That is substantive behavioral context an agent could not get from the annotations alone.

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?

Four short sentences, all front-loaded with the return shape first and the exclusions after. Every sentence carries distinct information (what is returned, masking guarantee, no input, no mutation), with no 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?

There is no output schema, so the description steps in to describe the return contents (masked references, readiness, next human step) and privacy guarantees. Combined with the annotations, an agent has everything needed to call this correctly and interpret the response.

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?

With zero parameters, the baseline is 4, and the description reinforces it by stating 'Takes no input,' matching the empty schema with additionalProperties=false. No further parameter detail is possible or needed.

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: returns the owner's connected US checking accounts used for paper checks, as masked references. It also distinguishes the scope by clarifying what the tool does not do (connect, change, verify), so an agent can place it precisely among the sibling list/draft tools.

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?

The 'for paper checks' framing and the explicit exclusion 'Does not connect, change or verify an account; the owner does that in their browser' give clear context and an exclusion, steering the agent away from expecting mutation. It stops short of naming an alternative sibling or an explicit when-to-use trigger, so it is a 4 rather than a 5.

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