Calculiva Cut Planner

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is low, and the description adds real behavioral context: how trim pieces are packed (all walls and types on shared stock) and that it compares this against one order per wall, ranked by total length bought, then offcut, then boards. It does not cover failure modes or size limits, but the added planning logic is substantive.

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?

Purpose and composition are front-loaded in the first clause, with the packing/comparison detail following. The second sentence is dense and slightly long-winded, but every clause carries information about outputs or optimization behavior.

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?

A rich output schema exists, so return values need no narration, and annotations carry the safety profile. The description covers composition, argument inheritance and the key packing/comparison rule; only explicit routing-away-from-siblings and any input limits are absent.

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 100% and the schema itself already explains every argument, including that stock, kerf and extra are shared. The description only restates that the same arguments apply and hints at the stock-length comparison; it adds little syntactic meaning beyond the schema, so baseline 3.

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 ('Builds one consolidated order sheet') plus exactly what the sheet contains (cartons, boards per stock length, rolls, offcuts, cut list, CSV). It is clearly the consolidating tool among the plan_* siblings, and it names those siblings explicitly.

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?

Explicitly routes the agent by saying to 'pass the same arguments as plan_flooring_order, plan_trim_order and plan_wallpaper_order', which tells the caller this is the one-shot combined alternative. It stops short of an explicit when-not (e.g. use plan_* individually if you only need one material), so it is clear context rather than a full decision rule.

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

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavioral context: offcuts flow forward room to room, 8 scenarios are evaluated, the tie-break chain (fewest cartons → least offcut → fewest planks), and the 3,000-plank call limit. This is meaningful disclosure of computation and limits beyond the safety profile.

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?

Purpose is front-loaded, but the body is a single sprawling run-on sentence with a long clause chain (scenarios, tie-breaks, waste allowance) that is hard to parse. Every clause is informative, yet the structure sacrifices readability for density.

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 an output schema present, the description needn't explain return values, yet it still notes a per-room link, which is helpful. Combined with the constraint disclosures and computation logic, it is largely complete for an 18-parameter planner, though it could say more about prerequisites or failure modes.

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 100%, so the baseline is 3. The description adds unit-handling ('lengths accept feet and inches') and explains the offset x reuse scenario space, but does not clarify individual parameters like minStarter, minJointSpacing, or clearance beyond what the schema already documents.

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 ('Plans') and resource (laminate, LVP, engineered plank flooring) with scope (1-12 rooms, rectangles or L shapes) and outputs (cartons to buy, per-cut tracing, best scenario). An agent can distinguish this from plan_trim_order or plan_wallpaper_order purely by the flooring/plank framing.

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?

Usage is implied by the scope details (needs plank size and planks per carton, up to 3,000 planks per call), but the description never states when to choose this over the sibling planners or states exclusions. The only hard boundary given is the 3,000-plank cap, which is more of a constraint than guidance.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds genuinely non-obvious behavior: the stock-length selection rule (least total length, then least offcut, then fewest boards), the first-fit-decreasing algorithm with the honest 'feasible, not proven optimal' caveat, and unit-parsing tolerance. These are traits an agent could not recover from the 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?

Purpose is front-loaded in the first clause and every sentence carries substance (outputs, optimization rule, algorithm caveat, units, return). The middle semicolon-chained sentence about tie-breaking is dense and slightly overloaded, but nothing is redundant.

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 35-parameter tool with an output schema and full schema descriptions, the description is largely self-sufficient: project types, optimization policy, algorithm quality, and the return artifact are all stated. The main gap is that it never clarifies which parameters apply to which project variant, leaving that cross-referencing to the schema.

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 100% across all 35 parameters, so the schema already documents every field including defaults and per-project applicability. The description's only parameter-level addition, 'Lengths accept feet and inches,' largely restates the schema's repeated unit examples, so baseline 3 is correct.

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?

Names a specific verb (plans) and resource (trim board order for board-and-batten, wainscoting, or picture-frame molding on one wall), and enumerates the concrete outputs (spacing, cut list, boards per retail length). An agent can distinguish this from the flooring/wallpaper planners and from build_order_sheet without opening the 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?

Usage is implied by the scoping phrase 'on one wall' and the project enum, and the mention of a returned plan link hints that a separate order-sheet tool exists. But there is no explicit when-to-use/when-not guidance and no named alternative such as build_order_sheet, so the agent must infer the boundary.

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

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

Annotations already declare this is a read-only, idempotent, non-destructive, non-open-world call, so the safety burden is lifted. The description still adds value beyond that: it discloses the external artifact produced ('a link to the full plan on calculiva.com') and the unit-parsing behavior ('Lengths accept feet and inches').

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 core action and tightly packed, with no filler sentences. It is a single long sentence, but each clause carries distinct information (inputs, outputs, units, return link).

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?

An output schema exists, so return-value detail is not required, yet the description still notes the plan link and comparison output. Combined with 100% schema coverage and clear annotations, the definition gives an agent enough to call the tool correctly; only routing guidance against siblings 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 100%, so every parameter (walls, rollWidth, rollLength, repeat, match, openings, trim, deductOpenings) is already documented in the schema. The description's brief parenthetical '(width, length, pattern repeat, match)' and the unit note merely restate schema content, so the baseline 3 applies.

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 ('Counts the wallpaper rolls to buy') and enumerates the concrete outputs: drops per roll, cut placement, match waste, and straight/half-drop/random comparison. The wallpaper domain cleanly separates it from plan_flooring_order and plan_trim_order without needing to name them.

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 description implies the context (estimating material before ordering wallpaper) but never states when to use this versus the sibling planning tools or any preconditions/exclusions. Usage must be inferred from the purpose statement alone.

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