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

With no annotations at all, the description must carry the behavioral load, and it does disclose two genuine traits beyond the schema: deterministic newest-first ordering and the pagination contract (has_more, next_cursor). It does not say anything about read-only semantics, rate limiting, or auth requirements, so the safety profile is left implicit in the word 'List'.

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?

Two compact sentences with zero filler: the core operation and ordering lead, filters follow, and the return shape is packed into the second sentence. Nothing is repeated from the schema unnecessarily.

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 seven-parameter read tool with no annotations and no output schema, the description covers the operation, ordering, main filters, and return envelope, which is most of what an agent needs. The gaps are the unmentioned date-range parameters and the absence of any explicit safety statement, which a mutation-free tool can largely get away with.

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%, and the description adds meaning for three of the seven parameters (status, order_id, customer_email) plus explains that cursor comes back as next_cursor. It says nothing about limit, created_gte, or created_lte, and does not clarify the enum values for status, leaving created_gte/created_lte dependent on the thin 'RFC 3339 timestamp' schema note.

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 ('List invoices') plus sort order and the filterable fields, so the agent immediately knows both what it does and the shape of the query surface. It implicitly separates from get_invoice (single record) but never names a sibling, so it stops short of full 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?

The mention of filterable fields implies usage contexts (find by status, by order, by customer), but there is no explicit guidance on when to prefer this over get_invoice for a known ID or list_payments for payment-level data. Usage is inferable but not stated.

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