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

With readOnlyHint=true annotation, the description reinforces safety by framing it as a read operation. It adds value by explicitly stating the 3000-char cap, the return shape ({ content }), and the empty-string behavior when unset, which goes beyond the annotation's minimal signal.

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 a single, dense paragraph that front-loads the core purpose and follows with important context about preferences and return format. It is slightly verbose but every sentence serves a purpose—no wasted words.

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?

Given no parameters, no output schema, and read-only annotations, the description adequately covers the tool's behavior, limitations (cap), and edge case (empty string). It is complete for a simple getter tool; missing only explicit sibling differentiation in usage guidance.

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 tool has 0 parameters, so the schema conveys all structural info. The description adds no parameter syntax, which is unnecessary. Baseline 4 is appropriate given the absence of parameters and the schema coverage being trivially complete.

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 reads account-wide custom instructions for AI agents, specifies the scope (user-level, across all models), and distinguishes it from model-level FINANCE.md. This is a specific verb+resource description that sets it apart from the sibling layerz_get_finance_md tool.

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 explains when to treat the instructions as standing preferences and notes they are delivered in MCP server instructions at session startープroviding context for when an agent might still call this tool. It mentions FINANCE.md overrides, which implicitly differentiates from get_finance_md, though it does not explicitly name that sibling.

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