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

Beyond the annotations it discloses substantive behavior: the platform fee is computed and frozen at open using ceiling on bps, the escrow is returned in state OPEN, and a replay with open_ref yields the original escrow with duplicate=true rather than a new one (E10). The conditional idempotency described is consistent with idempotentHint=false, which correctly reflects that idempotency only holds when open_ref is supplied.

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?

The definition is dense and front-loaded, leading with what is created and then the money-unit caveat and idempotency contract. Every sentence carries information, though terms like "ceil bps" and the bare code "E10" are left unexpanded for the reader.

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 money-moving mutation with an output schema present, this covers what an agent most needs before calling: unit conventions, fee freezing, returned state, and the exact retry contract. The remaining gap, per-parameter meaning for payer/payee/terms/currency/deadline, overlaps with the schema and is minor relative to what is disclosed.

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 0%, so the description carries the burden and it only partly does: amount_minor is defined precisely (positive integer, minor units/cents), open_ref's purpose is explained, and fee_bps behavior is implied by the fee-freezing sentence. payer, payee, terms, currency, and deadline receive no semantic treatment at all, leaving five of eight parameters undocumented.

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 opens with a specific verb and resource ("Open an escrow between payer and payee") and states the resulting state (OPEN) and return value (escrow_id). It is clearly distinct from siblings like fund_escrow or release_escrow by naming the opening act, but it never explicitly says how it relates to those siblings in the lifecycle.

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 gives concrete conditional guidance: pass open_ref=<your job id> so a replayed call returns the original escrow rather than minting a duplicate. That is real when-to-use guidance, but there is no explicit statement of prerequisites (e.g., that funding must follow) or when-not-to-use conditions.

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