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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the bar is lower, yet the description still adds real value: it enumerates what the report contains, notes that exact Xero payloads are included, and explicitly states 'Sends nothing' to reassure the agent no writes occur. Missing are volume/pagination expectations for large months, which keeps it at 4.

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?

Content is front-loaded with the 'month at a glance' framing, and the closing 'Sends nothing' is a high-value two-word clarification. The main sentence is a long run-on list, but each enumerated item (net/VAT/invoices, held-back invoices, no-job lines, price changes, payloads) conveys distinct return-content 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?

With no output schema, the description must convey what comes back, and it does so by describing the bill/line structure, the exception buckets, and the embedded payloads. Combined with annotations covering the safety profile, an agent has enough to call this correctly; only scale/ordering behavior is unspecified.

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?

There is a single required parameter with 100% schema coverage and a concrete format example ('YYYY-MM, for example 2026-11'), so the schema carries the semantics fully. The description adds nothing about the month argument, so the 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?

The description names a concrete output shape: one draft bill per supplier, one line per job, plus held-back invoices, unreferenced lines and price-change costs. That is far more specific than the title and lets an agent tell it apart from mutating siblings like push_bills_to_xero. It stops short of naming a sibling outright, so a 4 rather than 5.

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?

Usage is only implied: 'Sends nothing' signals this is a preview/report rather than the push step, which suggests it precedes push_bills_to_xero. There is no explicit 'use this when you want X instead of Y' statement or any stated prerequisite such as a Xero connection. Adequate but leaves the agent to infer the workflow position.

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