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

Annotations already declare destructive=true and idempotent=true, so the safety profile is covered; the description adds genuinely new behavior: delivery happens in the next session's handshake, no version is persisted (no rollback), and the tool is not exposed to model-scoped or read-only keys. This auth/visibility and delivery context exceeds what annotations provide, though reversibility could be stated more directly.

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 core action is front-loaded in the first clause, followed by format, length, clearing semantics, scope, delivery, persistence, and access constraints. Every sentence carries distinct information with no padding.

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 setter with no output schema, the description covers format, size limit, clearing behavior, scope of effect, when changes take effect (next session), persistence, and key visibility. 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% and the single 'content' parameter already documents the 3000-char max and empty-string clearing behavior, both of which the description simply restates. With one well-documented parameter, the baseline of 3 applies as no additional meaning is added.

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 (Replaces) and resource (account-wide custom instructions) with explicit scope, and the scope wording ('account-wide', 'apply across every model') distinguishes it from the model-scoped sibling layerz_set_finance_md. An agent can identify the operation without opening the 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?

Clarifies the clearing case ('an empty string clears them') and implicitly contrasts its scope with a model's FINANCE.md, which differentiates it from the finance sibling. However, it never explicitly states when to prefer this over siblings like set_finance_md or get_conventions, leaving selection partly to inference.

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