procurement_po_cycle

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

Annotations only provide readOnlyHint=true, and the description explicitly adds 'A DERIVED read over the live PO / receipt / match documents; posts nothing.' This confirms read-only behavior and adds that it computes over derived metrics, excludes open POs, and uses engine-recorded timestamps. For a read-only analytics tool with no destructive behavior, this is strong transparency.

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?

The description is one fairly dense paragraph, packed with useful details: metric definitions, window, grouping, exclusions, timestamp source, and read-only nature. It is informative but a bit dense, and could have been structured with bullets or separate sentences for the exclusions and grouping. Still, every sentence adds meaning, so it earns a 4.

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 read-only metrics tool with 4 mostly self-explanatory parameters (workspaceId, from_date, to_date, group_by), the description covers the core semantics: what is measured, over what population, in what time frame, and why it is a derived read. It doesn't detail the output shape, but no output schema exists, and a mention of what the response contains (e.g., list of metrics with average/p50/p90) would improve it. Still, the description is quite complete for an analytics tool.

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 description carries the burden for parameter semantics. It explains that from_date/to_date define the window, group_by presumably supports supplier grouping ('overall or grouped by supplier'), and the scope uses terminal states. It doesn't explicitly spell out each parameter name's format or allowed values, but it conveys the meaning of the date range and grouping role. Required workspaceId is mentioned in the description, so a 4 is warranted.

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 states the tool computes PO cycle-time metrics (average, p50, p90 days for order-to-first-receipt and order-to-full-match) over POs in a terminal state in a window, with grouping by supplier. This is a specific verb (compute aggregate metrics) + resource (POs in terminal state), and distinguishes it from siblings like po_list, po_get, po_open_lines, and other procurement_* analytics tools.

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?

It clearly states when to use: when you need cycle-time metrics over completed POs in a date range, optionally grouped by supplier. It also explicitly excludes open POs, and mentions the absence of sent_at stage. It doesn't explicitly name sibling alternatives or say when not to use it, but the scope is clear enough to differentiate from transactional PO tools and other procurement reports.

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