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

Goes well past the annotations: it discloses that reopening undoes a sign-off, that a reason is mandatory, and that the close is retained on the record as reopened rather than erased — which is what makes destructiveHint=false credible. It also declares a hard authorization rule (refused regardless of role) that no annotation conveys.

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 critical fact — human-only — is front-loaded and repeated for emphasis, which is defensible for a refusal. However, "Refused to you whatever your role" appears twice as a standalone sentence, and "Its period moves again with the record" is vague enough to be noise rather than information.

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, non-callable-by-agent mutation with no output schema, everything needed is present: who may invoke it, what it does to the sign-off, what is retained, and which close qualifies. There is no realistic gap left for an agent to guess at.

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 description coverage is 100% and the single parameter is fully documented as "Why it is reopened." The description's "with a reason" restates rather than enriches that, adding no format, length, or validation guidance. Baseline 3 is appropriate when the schema already carries the parameter semantics.

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 and resource ("Reopen the most recent close") and immediately scopes it to the latest close only, which cleanly separates it from the sibling gl_close_period and from gl_closes/gl_entries reads. An agent knows exactly what the operation is 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?

Gives the explicit when-not: "HUMAN-ONLY: this act is refused to you whatever your role ... Ask your human to do it." That is an unambiguous routing instruction rather than implied usage. It also bounds applicability ("Only the latest close can be reopened; earlier ones stay closed").

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