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

With empty annotations, the description carries the full burden and does well: it discloses the temporary restriction, admin-only undo, and the lock parameter's effect ('system locked, the customer cannot remove lock'). It also instructs a confirmation step. Some edge cases (e.g., in-flight transactions) are not mentioned, but the essential behavioral traits are covered.

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 description is structured with @param sections but suffers from verbatim duplication of the first sentence ('Temporarily restricts an account...') appearing twice. The @return line is generic and adds little value. It is not overly long but the redundancy and unnecessary repetition reduce conciseness.

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?

The description covers purpose, warnings, side effects, and all parameters thoroughly. Given the presence of an output schema, the generic '@return: a json object' is not a major issue. It lacks explicit reference to alternative tools, but for a sensitive mutation tool with no annotations, the description is quite complete and actionable.

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?

The @param block adds significant meaning beyond the raw schema (which has 0% description coverage). It explains where to obtain the token ('provided by /access/login'), clarifies account_fk as a database ID and not an account address, and details the lock parameter's behavior. All four parameters receive useful semantic context.

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 clearly states the tool's action: 'Temporarily restricts an account from performing any function that would result in funds existing the account' (despite the typo 'existing' for 'exiting'). It also adds important context like admin-only undo. However, it does not explicitly differentiate from sibling tools such as netfluid__access_pause or netfluid__account_resume, though the account-focused scope is implied.

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?

The description provides strong usage guidance: 'warn before using! Confirm (yes/no) before executing' and 'Can only be undone by an administrator' clearly indicate when and how to use the tool with caution. It does not explicitly name alternatives like account_resume or account_unlock, but the warning and context cover the key usage considerations.

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