BHX Fab Quote

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: accepted input format (text DXF from AutoCAD/Fusion/Inventor), the assumption of flat 2D geometry, the exact diagnostics reported, and the explicit scope limit that nesting is excluded. That is meaningful behavioral context an agent could not infer from the annotations.

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 dense sentences, front-loaded with the core action and outputs, then the conditional extensions and the scope exclusion. No filler or restatement of the title.

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 10 parameters, nested objects, and no output schema, the description carries the return-value burden and does so by listing the result fields and the two conditional result modes. Minor gaps remain around units handling and failure behavior on malformed files, but nothing essential to invoking it correctly 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 coverage is 90%, so baseline is 3; the description still adds value by explaining the conditional relationship between inputs and outputs (cut_speed → time with acceleration and pierces; pricing → price). It does not clarify units fallback, pierce_time_s, or quantity, but the schema already documents those.

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 ('Reads a flat 2D DXF') and enumerates the concrete outputs (parts, cut length, pierces, drawing problems), so an agent knows exactly what it gets back. It also scopes the tool negatively ('Sheet nesting is not included'), separating it from nesting tools, and its domain is clearly distinct from the STL/G-code/rates siblings.

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?

Conditional usage is spelled out well: 'With a cutting speed it also returns the cutting time... with pricing it returns a price', which tells the agent which optional inputs unlock which behavior. 'Sheet nesting is not included' is a useful exclusion. No sibling alternative is named explicitly, which keeps it from a 5.

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, so the description is free to add real behavioral context: the estimate is geometry-only, feature-blind to holes and corner radii, and capped at 60,000 triangles. That's exactly the kind of expectation-setting an agent needs. It stops short of saying whether the pricing block changes the return shape.

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 tight sentences: capability first, then limitation, then input cap. No filler. Slightly dense in the first sentence's output list, but every clause carries information.

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, the description does a decent job naming what comes back, but for an 8-parameter tool with a nested pricing object and quantity/setups concepts, it leaves the agent guessing how quantity or pricing extras affect the answer and what the numeric result looks like.

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 50%, and the description only gestures at parameters indirectly ('stock block' hinting at allowance_mm, 'material removal rates given' hinting at the material object). Units, defaults, and defaults for up/setups/quantity/machine_rate_per_hour are left entirely to the schema, so it neither compensates nor is required to.

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+resource ('Budget estimate for machining a part from an STL') and enumerates the computed outputs (stock block, material removed, surface area, roughing/finishing time, mass). It implicitly separates itself from the DXF and g-code siblings by working on STL geometry, but never names those alternatives.

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 'Based on volume and surface area only; holes and corner radii are not detected' clause is a useful applicability caveat, and 'before CAM' in the title nudges timing. However there is no explicit routing to analyse_dxf_for_cutting for 2D parts or estimate_gcode_run_time for exact CAM time, so when-to-use is only implied.

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 real operational context beyond that: the simulation model (rapid speeds, acceleration, tool-change time), the supported cycle families, the returned artifacts (run time, per-tool time, program size, warnings), and a hard 3,000-line ceiling. It stops short of saying what happens when the limit is exceeded (error vs. truncation) or how warnings are surfaced.

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 sentences, front-loaded with the simulation action, followed by returns and then the size limit. The long parenthetical of G-code cycles is dense but functional since it lets an agent check program support; only that enumeration slightly slows the read.

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, the description does the necessary work of listing what comes back (run time, per-tool time, size, warnings) and flags notable warning cases. For a 9-parameter tool with nested objects, the pricing/quantity/rate parameters remain unexplained in the description, which is the main gap.

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 67%, so the baseline is 3. The description reinforces the machine-model parameters (rapid speeds, acceleration, tool-change time) and dialect handling (inch/mm, absolute/incremental), but leaves pricing, quantity, machine_rate_per_hour and piece-time behavior entirely to the schema, and never explains that pricing turns the result into a quote.

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 a specific verb and resource ('simulates a CNC, laser or plasma G-code program') and enumerates the supported G-code feature set, which makes the input domain unambiguous. That domain (G-code text) cleanly separates it from siblings like analyse_dxf_for_cutting and estimate_cnc_from_stl 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?

Usage is only implied: an agent can infer this is the estimator for G-code files rather than CAD/mesh inputs, and the 'up to 3,000 lines' limit guides applicability. There is no explicit when-to-use/when-not statement, no mention of the siblings as alternatives, and no guidance on which process or machine preset to pick.

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?

The annotations already establish that this is a safe, read-only, idempotent operation. The description adds a useful behavioral caveat that the returned values are defaults and not authoritative quotes, but it does not describe return format or units.

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 no wasted language. The key point, that these are default example figures rather than quotes, 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?

For a simple no-parameter getter, the description is adequate, but there is no output schema and the description does not explain the shape or units of the returned presets and rates. The caveat about defaults is helpful but does not fully compensate for that missing return-value context.

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?

The tool takes no parameters, so parameter semantics are not a concern. The baseline score for a zero-parameter tool is 4.

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 a specific verb and resource: it returns example machine presets and material rates used by default. This distinguishes it from the sibling estimation/analysis tools, though it does not explicitly name those alternatives.

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 gives implied usage guidance by saying the figures are starting points, not quotes, and should be replaced by a shop's own values. However, it does not explicitly say when to call this tool versus the estimation siblings.

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