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 and delivers it: activating the series causes invoices to be finalized and emailed to the customer with no further click. It also discloses what the call returns, which no output schema provides.

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?

Front-loads the verb and resource, then the highest-risk behavioral warning, then the follow-up tool call, then the patch rule and return values. Every sentence is doing work; nothing is redundant with the schema or annotations.

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?

With 10 parameters, 50% schema coverage, no output schema and a mutation that has external side effects, the description covers the dangerous paths and the return shape. The remaining gap is the silent behavior of the automation flags (auto_send, auto_finalize) and notes, which an agent must infer.

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 50%, and the description compensates for the most consequential fields by explaining the is_active true/false meaning and the follow-up behavior of next_invoice_date, plus naming payment term, name and reference as editable. It leaves notes, auto_send and auto_finalize unexplained, which are still undocumented in both places.

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 ('Change a recurring invoice profile') and immediately names the concrete editable facets (is_active, next/end date, automation flags, payment term, name/reference). This is clearly distinguishable from create_recurring, list_recurring and generate_recurring, which appear as siblings.

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 explicit when-to-use conditions: setting is_active=true only after the user confirms start date and frequency, and calling generate_recurring right after when next_invoice_date is today or earlier. It also states the patching convention ('Pass only the fields to change'), which prevents accidental overwrites.

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