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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value beyond that: it enumerates exactly what a detail call returns — lines, a per-month payment calendar compared to budget, and warning categories (late arrival, MOQ, budget overrun, unverified price). It does not mention pagination or result-size limits for the list mode, which keeps it from a 5.

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?

A single sentence that opens with the resource and branches immediately into the two usage modes, then packs the return contents into a parenthetical. Zero filler, nothing redundant with annotations, and the highest-value information is front-loaded.

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 and no parameter descriptions, the description carries the burden of explaining return contents, and it does that well by naming lines, payment calendar, budget comparison, and warning types. Annotations cover safety. The only missing piece for a one-parameter read tool is explicit guidance on pagination or volume in list mode.

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 0%, so the lone optional plan_id is undocumented in the schema and the description must compensate. It does so implicitly by contrasting 'list them' with 'one plan with its lines', which tells an agent that supplying an identifier narrows to a single plan. But it never names plan_id, never states that omitting it returns all plans, and gives no format expectations, so compensation is only partial.

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?

The description names a specific resource (purchase plans) and states both modes of operation: listing all plans, or fetching one plan plus its lines, monthly payment calendar against budget, and open warnings. That is far more than a restatement of 'Get purchase plan'. It stops short of distinguishing itself from look-alike siblings such as plan_status or proc_shortages, so it lands at 4 rather than 5.

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 list-vs-single distinction implies when to call each way ('list them, or one plan with its lines'), which is usable guidance for the optional plan_id. However, there is no explicit statement about when to prefer this over plan_status or proc_shortages, and no exclusions. Usage is implied rather than spelled out.

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