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

The annotations only declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false. The description adds crucial context annotations do not: explicit activation relinks matching lines and reposts affected payslips, activation failures should be inspected, and superseded rubrics cannot be modified. These are material side effects that go well beyond the structured hints.

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?

Four front-loaded sentences with no waste: purpose, ID sourcing, payload shape, and behavioral caveats. Every sentence carries actionable 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?

The description covers purpose, ID sourcing, partial-update behavior, cascading activation effects, and immutability, which is good given the output schema handles return values. However, for a 19-parameter mutation with low schema coverage, it omits what status transitions are permitted and what most fields mean, leaving the agent under-equipped to invoke it correctly.

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 only 21% across 19 parameters, so the description must compensate. It adds useful partial-update semantics ('Supply only fields to change') and tells where the required ID comes from, but it leaves almost all other fields undocumented—including which status transitions are actually permitted, and the meaning of line_kind, line_side, the tax scheme enum, and the various boolean flags.

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 states a specific verb ('Correct') and resource ('one payroll-line rubric'), plus a distinct second action ('request a permitted status transition'). This clearly separates it from siblings like well_create_payslip_line_rubric and well_delete_payslip_line_rubric.

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?

It tells the agent exactly where to get the required payslip_line_rubric_id ('from well_query_records on payslip_line_rubrics') and how to shape the payload ('Supply only fields to change'). It also gives a clear exclusion ('Superseded rubrics are immutable') but does not explicitly compare itself to create or delete siblings.

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