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

Annotations only declare readOnlyHint=false and destructiveHint=false, so the description carries real weight here and delivers: the create-vs-edit field contract, the immutability of employee and leave type after creation, the sign convention for days (positive grants, negative consumes leave), and the key side-effect disclosure that movements change leave balances only and post nothing to the ledger. It omits permission/authorization requirements and any indication of what the save returns.

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?

Three sentences, no filler, and the create/edit split is front-loaded so the agent learns the primary routing rule before the field details. Every clause carries operational information (required inputs, mutable fields, balance-only effect).

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 mutation tool with no output schema, the description covers the create path, the edit path, immutable fields, and the ledger side-effect, which is close to complete. The one gap is the mismatch with the schema: required is [], yet creation is described as needing employee, leavetype, kind and days; the description never flags that conditional requirement explicitly or states what the tool returns on success.

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 0% across 7 parameters, so the description must compensate and largely does: id (edit selector), employee, leavetype, kind with its two enumerated values, days with sign semantics, and date/notes as edit-time fields. Nearly every parameter gets meaning beyond its bare name, which is exactly what a 0%-coverage schema requires.

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 specific verbs (create or edit) against a specific resource (a leave opening balance or adjustment / leave movement), and the second sentence pins down exactly what fields exist in each mode. An agent can distinguish this from save_leave_request or save_leave_type purely from the description, since the resource and its effect on leave balances are named.

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?

Explicitly routes the agent: supply employee/leavetype/kind/days with no id to create, supply an id to edit, and it names exactly which fields are mutable versus fixed on edit (employee and leave type are fixed). It does not name sibling alternatives such as list_leave_movements for lookup or save_leave_request for approvals, so it falls short of a full when/when-not/alternative statement.

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