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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: an authorization requirement (caller must be payer or payee) and a cross-mode visibility quirk. It still doesn't say what an errored or not-found call looks like, but the additions are substantive.

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, front-loaded with the return payload, then access rules, then the REST endpoint mapping. Every sentence earns its place and none of it repeats structured fields verbatim.

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 present, the description must describe return values and it does so explicitly. Access constraints and mode scoping are covered, and the annotations handle the idempotency/read-only profile, so an agent has everything needed to call this correctly.

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%, including the job_… id format and the api_key fallback chain, so the schema already carries the parameter burden. The description adds no syntax or format detail beyond what the schema states, making the baseline 3 appropriate.

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 ('Return an escrow job's status') and enumerates the exact payload the agent will receive (status, held amount, release fee, payer/payee wallets). The read-only framing is clearly distinguishable from the sibling mutators create_job, release_job, and refund_job.

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?

Gives a concrete eligibility precondition ('The caller must be the payer or the payee') and an exclusion ('A job from another Stripe mode is not visible'), which tells the agent when this call will fail or return nothing. It does not name an alternative tool for cases that fall outside those conditions, so it stops short of full when/when-not/alternatives guidance.

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