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

Adds substantial behavior beyond the annotations: it names the exact funding source (authenticated payer wallet), enumerates the rejection conditions (amount_credits < 1, payer == payee, missing/other-mode payee wallet, insufficient balance), and spells out the idempotency contract that a retry returns the same job without double-debiting. The annotations already cover readOnly=false and idempotent=true, so this is useful amplification rather than the sole disclosure, and the one remaining gap is the response shape.

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 tightly packed sentences with the escrow purpose front-loaded, followed by debit mechanics, failure conditions, and idempotency. Every clause carries information and nothing is redundant.

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 mutation tool with no output schema, the description covers funding, validation failures, idempotency, and the API equivalent, which is most of what an agent needs to invoke it safely. It never says what the created job object returns (job id, status field), which is the one item an agent must infer from 'returns the same job', so it is strong but not fully complete.

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 every parameter is already documented in the schema, and the description largely restates that content (amount_credits minimum, idempotency_key retry behavior, payee receiving credits on release). It adds the cross-field rule that payer must differ from payee, but that is a small increment over an already complete schema, so the baseline of 3 is 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 concrete verb and resource ('Hold credits in escrow for a job') and pins down the exact lifecycle moment, which cleanly separates it from the sibling release_job and refund_job tools that act on an existing job. The closing 'Same as POST /v1/jobs' anchors it to a known API surface, so an agent can place it without opening the 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?

Gives clear context for when this tool applies: the escrow-hold step whose credits are later released or refunded, which implicitly routes the agent to release_job/refund_job for those follow-ups. It stops short of any explicit when-not or named alternative (e.g. create_checkout or purchase), so the guidance is contextual rather than directive.

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