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

With no annotations, the description carries the full burden. 'Inspect' strongly implies a read-only, non-mutating operation and the output list is transparent, but it never explicitly confirms safety, and it omits any cost or performance warning for the potentially expensive wall_samples sampling mode.

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 purpose and output list are front-loaded in the first two sentences, and the optional-parameter behavior is grouped at the end. The genus paragraph is useful but slightly verbose, with a mild sales pitch ('far more reliable than "looks about right"') that is not strictly necessary.

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?

There is no output schema or annotation coverage, so the description must convey return content, and it does so by enumerating every metric returned plus the semantics of genus. It is nearly complete for this inspection tool; only the 'name' parameter and any cost caveats remain unaddressed.

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 0%, so the description must compensate, and it does for two of three parameters: slices is explained as 'z heights in mm to also measure cross-section areas' and wall_samples as sampling minimum wall thickness when >0. The required 'name' parameter is left undefined, though its meaning is self-evident from context.

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 opening sentence names a specific verb and resource ('Geometrically inspect a model you already built') and enumerates the concrete outputs (watertightness, genus, volume, etc.), so an agent knows exactly what comes back. It does not explicitly contrast itself with the similar-sounding siblings look_at_mesh or describe_model, leaving that differentiation to inference.

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 a clear context of use: 'returns numeric evidence you can use to decide whether it came out right,' and notes the optional slices/wall_samples modes for deeper checks. It does not state when NOT to use it or name an alternative sibling, so the routing guidance is incomplete.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses the kinds of information returned, but does not state that the operation is read-only, whether it has side effects, what happens if the model does not exist, or any permission requirements.

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 two short sentences with no wasted text, and it front-loads the returned information before the usage note. It could be slightly more structured, but it is efficient.

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 must explain return values, and it does list major categories. It remains incomplete for the single required parameter and for error or not-found behavior, leaving some gaps for an agent invoking the 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?

There is one required parameter, 'name', with 0% schema description coverage. The description implies the name identifies 'a model you built', but does not explain the expected format, uniqueness, or source of the name, so it fails to compensate for the missing parameter documentation.

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 retrieval action and enumerates what information is returned: parameters, topology, bounding box, and files. It is clearly a metadata lookup for a built model, though it does not explicitly name how it differs from siblings like list_parts or check_mesh.

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 a concrete usage occasion: mid-session, to recall the parameters a model was built from. However, it does not name alternatives or describe when not to use this tool, leaving routing guidance implicit.

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?

With no annotations, the description carries the full burden and does well: it discloses a hard pre-write gate (non-manifold edges, non-positive volume, NaN vertices, fragmented shell are refused), distinguishes that watertightness only warns, and documents the force override. It stops short of stating where files are written, whether existing files are overwritten, or what is returned.

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-loads the core action and format list, then the gate behavior. Every sentence carries information, though the gate explanation is dense and could be trimmed slightly.

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 4-parameter mutation tool with no output schema and no annotations, the description covers validation/override behavior well but omits the required `name` parameter's meaning, the stl_binary toggle, and any return/output location, leaving gaps an agent must guess at.

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 must compensate. It documents formats and force (including the gate override), but leaves the required `name` parameter and `stl_binary` (binary vs ASCII STL) entirely unexplained, so it only partially closes the coverage gap.

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 (export) and resource (the model) and names the concrete output formats (STL for printing/slicing, OBJ+MTL for DCC), which is exactly the kind of differentiation needed against siblings like check_mesh and look_at_mesh. An agent can tell what this produces 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?

Explains the selection context (downstream tools), the default of both formats, and the force=True override for the validation gate. It does not explicitly route to siblings such as check_mesh as a pre-flight step, but the when-to-use and override conditions are clear.

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?

With no annotations, the description carries the load and does disclose a real failure mode (guessing a parameter raises unknown_parameter) and the shape of the return (parameter names with defaults and types). It is implicitly a safe read, though it never says so outright.

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 short sentences, zero waste, with the primary action first and the workflow hint second. Nothing padded.

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 zero-parameter discovery tool with no output schema, the description covers what it returns and why to call it before modelling. An agent has everything needed to invoke it correctly.

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 zero parameters, so the baseline is 4. The description adds that the listed entries expose tunable parameters with defaults and types, which is useful context about what the caller gets back.

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 (List) and resource (built-in parametric parts) plus scope (tunable parameters with defaults and types). It is clearly a discovery tool, distinct from the make_part/make_lattice siblings that create geometry.

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?

Gives explicit when-to-use guidance: 'Call this before modelling to get the exact parameter names.' It even states the consequence of skipping it (unknown_parameter). No explicit when-not or named alternative, but the context is unambiguous.

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?

With no annotations, the description carries the full behavioral burden and does well: it discloses that the render returns image content, that the image always precedes the JSON summary, and that turntable_frames>0 writes a GIF file for the human and returns its path. It does not cover error behavior or mesh-missing cases, but the key side effect and return ordering are explicit.

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 core render-and-return purpose is front-loaded with bold emphasis, and the remaining guidance is compact. The structure is easy to scan, though slightly informal.

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 render tool with no output schema and no annotations, the description adequately explains the return format and two parameters. However, six of eight parameters have no semantics anywhere, and there is no mention of prerequisites or failure modes, so it is only minimally sufficient.

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% across 8 parameters, so the description must compensate. It only explains views ('four'/'single'/'grid') and turntable_frames behavior; name, size, azimuth, shading, elevation, and wireframe remain entirely undocumented, leaving most parameters opaque.

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 (render) and resource (model), and frames the purpose as self-verification. It does not explicitly differentiate from sibling check_mesh or describe_model, but the action is unambiguous 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?

The description recommends 'views: four' as the starting point, implying primary usage. However, it gives no explicit when-not condition or comparison to siblings like check_mesh, leaving the agent to infer when rendering is preferable.

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?

With no annotations, the description carries the full burden and does disclose useful behavior: res is called out as a precision knob with an 8x-slower cost at 128, and the resulting voxel edge is reported back. However, it says nothing about persistence (whether a part is saved under name), permissions, or what a failure looks like, leaving meaningful gaps for an operation that creates geometry.

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 one sentence, then parameters are documented as tight labeled lines with no filler. Every line adds a fact an agent needs (defaults, units, speed tradeoff) rather than restating the schema.

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 9-parameter, zero-annotation, no-output-schema tool, the description covers parameters well but leaves the agent unsure what the call produces (a stored part? geometry?) and what 'name' does. It is adequate but not fully self-sufficient for a tool this complex.

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 0% and parameter titles are bare, so the description is the sole source of meaning, and it delivers: primitive enumerations, the number-vs-[x,y,z] polymorphism of size_mm, the size/res voxel relationship, and the period_mm-defaults-to-cell_mm coupling. Only 'name' goes unexplained, which is a minor omission against otherwise excellent compensation.

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 opening line states a specific verb+resource: 'Model free-form geometry with signed distance fields: lattices, porous structures, implicit surfaces.' An agent can tell this is the geometry-generation tool, distinct from sibling utilities like check_mesh or describe_model. It does not explicitly contrast with make_part, which is the most likely point of confusion, so it falls short of a 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 description gives operational guidance ('Start at 64', 'omit it to use cell_mm as a cube') but never says when to choose this tool over make_part or when a lattice vs. shell is appropriate. Usage is implied through parameter notes rather than stated selection criteria.

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?

With no annotations, the description carries the full burden and does disclose some behavior: it returns a topology verdict, unknown `params` keys are reported explicitly rather than silently ignored, and the result is session-stored. It omits anything about failure modes, auth, or whether the build consumes resources, so it is only partially transparent for a mutation-style tool.

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 core action followed by return value and session semantics. No filler, though the parenthetical example list is slightly dense.

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 and no annotations, so the description must do more work. It covers the return type at a high level (topology verdict) and the session model, but leaves `params` structure and error behavior unspecified for a 3-parameter build 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 coverage is 0%, so the description must compensate. It does add meaning for each of the three params — `part` values come from list_parts, `name` is the session handle used by other tools, and `params` rejects unknown keys — but it never describes the shape or expected keys of `params`, leaving the main data-carrying parameter under-specified.

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 ('Build a part from the built-in parametric library') and enumerates concrete examples (gear / vase / torus knot / lattice coupon). It does not explicitly differentiate itself from the sibling make_lattice, which is the closest overlap, so it stops short of a 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?

Routes the agent to list_parts for valid `part` values and notes the model can be referenced by other tools, which implies downstream usage. However there is no explicit when-to-use vs make_lattice, and no statement of prerequisites or when-not to call it.

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