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

Annotations already declare readOnlyHint and destructiveHint=false, but the description adds genuinely new behavior: newest-first ordering, the 20-per-call ceiling, and the important default that status='open' silently excludes cancelled and archived orders. That default-filter disclosure prevents a common wrong result set and is not derivable from the annotations or schema.

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 the resource and scope, then filters, then the sibling pointer to erp_order_get. It is dense but nearly every clause carries information; the only wasted token is the trailing 'Read-only', which merely repeats readOnlyHint=true.

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 correctly enumerates the returned fields (number, date, client, total with currency, status, unpaid-invoice flag, source), so an agent knows what it can report without a trial call. For a four-parameter read-only list tool, nothing material is missing.

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 description coverage is only 25% (search alone is documented), and the description compensates well by explaining that search matches order number or client name, enumerating status meanings with the default, and interpreting payment as unpaid/paid. 'limit' is covered only indirectly via 'At most 20 per call', leaving its trade-off with the status scope implicit.

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 — the company's sales orders from the ERP — plus the scope that matters (includes orders pushed in from the connected online shop). It also names the sibling erp_order_get for a single order's lines, so an agent can separate the two without opening either 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?

Gives concrete trigger phrasing for the common intents («покажи замовлення», «неоплачені замовлення») and explicit routing to erp_order_get for line-level detail. The filter semantics (default 'open' vs 'all', what 'open' excludes) are spelled out, which is exactly the when-to-use context an agent needs.

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