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

Annotations already declare the operation is a non-read-only, non-destructive write. The description adds real context beyond that: approval is handled internally by the gateway (citing audit C-03 as the reason the public approve step was removed), and it names the return value (transaction hash). It does not cover failure modes or funding limits.

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?

Content is front-loaded with the action, then the critical approval caveat, then the return value. The parenthetical audit reference is informative justification rather than padding, though it is the one element an agent could do without.

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 single-parameter mutation with no output schema, the definition covers the action, the surprising internal-approval behavior, and the return shape, which is enough to call it correctly. Gaps are minor: no note on gas, token allowances, or error conditions.

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 for the single address parameter is 100%, so the baseline is 3. The description lifts this slightly by constraining the acceptable input to an escrow address that was created through the protocol, a non-obvious restriction given that generic escrow siblings exist.

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 (Fund) and resource (protocol-created escrow) plus the execution context (on-chain). The qualifier "protocol-created" separates it from the generic escrow siblings such as protocol_create_escrow and get_escrow, so an agent can identify the right tool without opening a 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 explicit negative guidance: "do NOT call a separate approve first; fund directly," which prevents a common multi-step mistake. It does not, however, spell out prerequisites such as the need for a prior protocol_create_escrow or token/allowance requirements, so the routing guidance is clear but incomplete.

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