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

Goes well beyond the single destructiveHint annotation by disclosing the internal call pattern (one read per product, bounded to 3 or one full product-list read, then ONE POST), the non-idempotent retry policy, and the concrete side-effect boundary (no stock changes, no money moves, order stays unlocked). This is exactly the behavioral detail annotations cannot convey.

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-loaded with 'WRITE' and the resulting status, which is the most decision-relevant fact, and the rest is dense but information-bearing. The middle sentence is long and packs three distinct behaviors (lookup scope, single POST, no retry) into one clause chain, which costs a little readability.

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 write tool with no output schema and only a destructiveHint annotation, the description supplies the state the record lands in, the side effects, the lookup and HTTP behavior, and the error-recovery path. Nothing an agent needs to call this correctly and safely is missing, and return-value detail is unnecessary since no output schema is declared.

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 100%, so the baseline is 3, but the description adds runtime semantics not in the schema: per-item product resolution happens before the POST and an unknown SKU aborts the entire request. It does not touch the other five parameters (order_id, notes, reference_number, destination_facility_url), so it only partially extends the schema's meaning.

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 ('Creates a purchase order for a supplier') and pins down the exact resulting state ('status ORDER_CREATED, i.e. an editable draft'). It also explicitly enumerates what it is not (locked, received, completed, emailed), which no sibling write tool would share, so an agent can distinguish it immediately.

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 clear operational context: products are looked up first, the call is never retried, and 'check finale_list_orders before repeating it after an error' names a concrete sibling for verification. It does not state prerequisites such as needing a supplier_party_id sourced from finale_list_parties (that is only in the schema), so it stops just short of full when/when-not guidance.

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