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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces rather than merely repeats that by clarifying the tool never approves. It also discloses return content beyond the schema: the field set of pending payments, the approver role, and that not-ready payments are included with lifecycle state and reason. It omits whether the access_key parameter must match the run's creator, and says nothing about result size or ordering.

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?

Two sentences, front-loaded with the scope and absent of filler; every clause carries information the agent needs. The first sentence is dense, packing two payment categories and six field names into one line, which hurts scanability slightly but is not wasteful.

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?

With no output schema, the description must explain the return shape, and it does so concretely (pending vs. not-ready, plus the key fields). Since annotations already cover the read-only safety profile, the remaining gaps are minor: ordering/pagination and empty-run behavior are unstated. It is complete enough for an agent to call correctly and interpret the result.

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 100%, so run_id (pr_... or pr_sample) and access_key are already documented at the schema level. The description adds the framing that results are scoped to a payment run, which reinforces run_id's meaning, but says nothing about which access_key value is valid or what happens on mismatch. Baseline 3 is appropriate when the schema carries the parameter burden.

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 names the exact resource and scope ('For a payment run') and enumerates what comes back: pending payments with amount, route, assessment, approval_digest, approver role, plus not-ready payments with lifecycle state and reason. It is easy to distinguish from approve_payment_run because it explicitly disclaims approving. It falls short of 5 only because the leading phrase is a scoping clause rather than an explicit verb like 'List' or 'Get', which matters given the tool's name misleadingly implies a mutation request.

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 states the positive context ('For a payment run') and gives an explicit exclusion plus the correct alternative: 'Never approves: a named person approves with approve_payment_run.' That routes the agent away from the most likely confusion with a similarly named sibling. There is no explicit 'use this when you need X' sentence or prerequisite note, so it stops just 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.