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

Annotations already declare readOnly=true, idempotent=true, destructive=false, so the safety profile is covered. The description adds value beyond that: default ordering (newest first), the exact field set returned for a single order, and the semantic that 'open' means sent or partial — a filter meaning an agent could not derive from the enum alone. It omits pagination behavior despite limit/offset existing.

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?

Very dense and front-loaded: the primary mode-switch leads, the filter list follows. Nearly every clause carries information. The trailing 'Free.' is terse to the point of ambiguity about whether it means no cost or no filtering restrictions.

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 7-parameter read tool with no output schema, the description does describe what comes back in the single-order case and what the list ordering is. The remaining gap is pagination semantics (default 50, max 200 via limit/offset) and whether supplier name performs fuzzy matching — modest omissions for a read-only tool.

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 57%, so the description needs to compensate, and it partly does: it explains the status filter vocabulary and, importantly, defines 'open' as sent-or-partial, which the schema enum does not. It also clarifies supplier and created from-to filtering. It leaves limit/offset/defaults and the supplier name-vs-id matching rules unexplained.

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?

Distinguishes two concrete modes: single-order read ('that order in full') versus a filtered, newest-first list. The content enumerated for the single-order mode (lines with received/billed amounts, PDF link, bills, history) makes the resource unambiguous. It does not explicitly name the sibling list tools it is not (e.g. purchasing_list_bills, purchasing_list_supplier_items), so it stops short of full sibling differentiation.

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?

'With order: ... Otherwise ...' gives clear internal routing between the two modes, which is genuinely useful. However, there is no guidance on when to reach for this tool versus purchasing_list_bills, purchasing_list_supplier_items, or purchasing_report, and no exclusions or prerequisites are stated.

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