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

Annotations already declare read-only/idempotent/non-destructive, but the description goes well beyond: it discloses the storage_deposit step omission that causes failures, that it returns the 'exact fix and its NEAR cost', that it catches sending to the token contract itself, and that data is 'live from the NEAR RPC'. It also transparently describes the pricing/auth model.

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?

Front-loads the core question and verdict tokens, then the checks, then the fix behavior, then inputs, then pricing. Dense but every block earns its place; the billing/marketing tail is the longest single component and slightly dilutes the read.

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?

An output schema exists so return values needn't be restated, and the description still covers the verdict semantics, required inputs, and the live-data source. Nothing an agent needs to invoke it correctly is missing.

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 parameters are documented; the description still adds value by explaining the conditional semantics of the optional params — 'With from and amount, also checks the sender holds enough' — which the schema alone does not convey.

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?

Opens with a specific question-form verb+resource ('Will this NEAR token transfer go through? GO / HOLD / STOP') and enumerates exactly what it verifies: token reality/pause state, receiver existence, registration/storage_deposit, and sender balance. The 'NEAR' scoping cleanly distinguishes it from chain-specific siblings like b20_transfer_preflight.

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?

Explicitly states the trigger condition: 'Before sending a NEP-141 token on NEAR.' It clearly names the case it governs, though it doesn't call out an alternative tool or state when NOT to use it (e.g., for swaps or non-NEP-141 assets).

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