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

Annotations only declare non-read-only, non-idempotent, non-destructive; the description adds the substantive traits that matter: the operation is hard-blocked for the agent regardless of role, what state the period ends in (journal kept with totals and a hash), and how subsequent changes are handled (corrections in the next open period). This is behavior the annotations cannot convey.

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 constraint (HUMAN-ONLY / refused to you) is front-loaded and the effects are stated compactly. However 'refused to you whatever your role' is effectively repeated twice in adjacent sentences, which is wasted space given inherently limited description budget.

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 2-parameter, no-output-schema mutation, the description covers everything an agent needs: whether it may call it, what to do instead, and the resulting state. No return-value explanation is required since there is no output schema.

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 both parameters (through, reason) are documented there with format and an example; the description adds no additional meaning about parameter semantics. Baseline 3 applies.

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+resource (close the books through a day) and defines the semantic effect precisely – journal frozen, figures stop moving, later changes become corrections. It is clearly distinguishable from gl_reopen_period and gl_checklist by naming the checklist as the agent-facing alternative.

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?

Explicit and unambiguous about when this tool should not be called ('refused to you whatever your role'), who must perform the action (the person or the accountant), and the exact substitute workflow: show gl_checklist, then the human closes it in the app. This is a textbook when-not/alternatives statement.

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