List purchase order links

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

Annotations already declare readOnlyHint/idempotent/non-destructive, so the safety profile is covered. The description adds real domain behavior the annotations cannot: links are reference-only and 'never add to committed cost,' which prevents an agent from misreading these rows as cost-bearing.

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?

Three compact sentences, front-loaded with what is listed, then the row semantics and cost caveat, then the filtering hint. No filler, though the cost caveat sentence is slightly tangential to invocation.

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?

No output schema exists, so the description correctly takes on describing the returned row shape. Combined with complete schema coverage for pagination and filters, an agent has what it needs; only the exact response envelope is unstated.

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 baseline is 3. The description goes further by framing the four ID filters and disclosing the mutual-exclusivity constraint on the returned rows (only one of work_order_id/pm_schedule_id/project_id is ever populated), which the schema does not state.

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 the extra records a purchase order is linked to') and immediately clarifies the return semantics: each row has exactly one of work_order_id, pm_schedule_id or project_id. This is enough to distinguish it from get_purchase_order_link and list_purchase_orders.

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?

Ends with 'Filter by any of those four IDs,' which implies when the tool is useful, but there is no explicit when-not guidance and no named alternative (e.g., use get_purchase_order_link for a single link). Usage is implied rather than stated.

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