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

Annotations already flag destructiveHint=true and idempotentHint=true; the description adds real value on top by stating that every change is retained in the line's history (so edits are auditable/reversible) and by naming the governing permission ('the project budget's write rule'). It also discloses that null actively clears category/date/taskId/note, which is the destructive behavior an agent most needs warned about.

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, front-loaded with the verb and affected fields; the null-clearing rule and the history/permission notes each earn their place. The embedded parenthetical example about a cancelled order is slightly verbose but clarifies the enum behavior.

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 essentials: which fields change, how to clear them, that history is preserved, and what access is required. Only the response shape and failure modes (e.g., invalid costLineId or cross-project taskId) are left unstated.

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 88%, so a baseline of 3 applies, but the description goes further by explaining the patch-only convention and demonstrating status transitions ('back to EXPECTED when an order is cancelled') and that amount is in the project currency. Those are semantics an agent would otherwise have to infer from individual parameter descriptions.

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 opens with a specific verb and resource ('Change a cost line') and immediately enumerates the mutable fields, which cleanly separates it from create_cost_line, list_cost_lines and get_cost_line_history. An agent can tell exactly what this tool does 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?

'Pass only the fields to change' establishes patch semantics explicitly, and the pointer to get_cost_line_history tells the agent where to verify results. It stops short of naming when to use update vs. create/re-create a line, but the mutation context is unambiguous.

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