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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, yet the description still adds real value: it is fast because it performs no slicing, it computes overhangs across six orientations, and it returns advice rather than raw numbers. That is meaningful behavioral context an agent cannot get from the annotations alone.

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 sentences, both front-loaded: the first enumerates what is computed, the second gives the usage directive and the format limitation. Every clause carries information; nothing is 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?

There is no output schema, so the description compensates by listing the returned measurements and recommendations in detail. Combined with the format restriction and the performance note, an agent has everything needed to select and 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?

With a single required parameter at 100% schema coverage, the schema already documents `path` as an absolute STL/3MF path. The description reinforces the same format restriction (STL/3MF, not STEP/OBJ), adding modest corroboration rather than new semantics.

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 (analyze) and resource (model geometry) and then enumerates the concrete outputs: dimensions, volume, bed fit, footprint, overhangs/bridges across 6 orientations, best orientation, and support/brim advice. The format scope (STL/3MF only) further distinguishes it from sibling tools like slice_model and inspect_3mf.

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?

"Use it first on any model" gives an explicit sequencing directive, and "STEP and OBJ files are not supported" sets a clear eligibility boundary. "No slicing" implicitly contrasts with slice_model, but no sibling is named directly, which keeps it just short of 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 readOnlyHint, idempotentHint and destructiveHint=false, so the description need not argue safety; it adds genuine context by clarifying that no slicing occurs and specifying what is compared and reported (flow per line type against max flow, the speed actually reached when capped). It does not describe auth requirements, performance cost, or the shape of the returned findings, which keeps it short of 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?

Two compact sentences, front-loaded with the purpose and the 'without slicing' qualifier before the detail list and the usage routing. No padding; the only near-waste is the two-word 'Read-only' sentence that duplicates the annotations.

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 one-parameter read-only tool with rich annotations this is nearly complete: the agent knows what is inspected and when to call it. Since there is no output schema, the description would ideally say a bit more about how findings are returned (list of issues vs summary), which it only hints at by naming the checks.

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 100% with a single required 'path' parameter whose description already pins it to an absolute Bambu 3MF path, so the schema carries the parameter burden. The description adds only the contextual fact that the file is read without slicing, not any format or constraint detail beyond the schema.

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?

'Check a 3MF project's settings without slicing' gives a specific verb and resource, and the following clause enumerates exactly what is validated (volumetric flow vs filament max, machine speed limits, cooling, per-material pitfalls). It also names slice_model as the sibling that reports the same checks, so the agent can separate the two without opening either 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?

'Use it before slicing a project' gives an explicit trigger condition, and 'slice_model reports the same checks on its result' supplies the alternative and the condition under which this tool is unnecessary. Both when-to-use and the competing option are stated outright.

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 read-only and idempotent, so the safety bar is low. The description adds valuable context: inheritance is resolved, only differing settings are returned, and unknown names cause failure. It does not describe pagination or limits, but the output schema exists.

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 with the core behavior front-loaded, followed by usage guidance and a failure note. No wasted wording.

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 and annotations covering safety, the description provides everything an agent needs: scope, return behavior, usage routing, and failure 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 coverage is 100%, so baseline is 3. The description adds meaning beyond the schema by enforcing that the two presets must be the same type and that unknown names cause failure, which shapes correct invocation.

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 (compare), resource (presets), scope (same type, only differing settings), and return shape (setting, value A, value B). Clearly distinct from get_preset, which is named as the read-one alternative.

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 names use cases (see what a user preset changes from a Bambu preset, how two profiles differ) and routes the agent to get_preset for full reads. Also states the failure condition when a name is unknown.

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?

Adds genuinely non-obvious behavior beyond the annotations: results are written under output/ and the original is never modified, which tells the agent this is a non-destructive write with a known artifact location. It also discloses the parallel batching. It does not say what happens if one variant fails or roughly how long a batch takes.

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, each carrying a distinct load: what it does, what it produces and its side effects, and when to prefer a sibling. The core action is front-loaded and nothing is 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?

With no output schema, the description usefully enumerates the returned comparison metrics (time, weight total and per plate, % difference from the original, checks) and the output location. The remaining gap is failure semantics for a multi-variant batch, which matters for an 8-parameter mutation 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 100% and each parameter (plate, models, machine, process, variants, filaments, include_original) is already documented in the schema with examples. The description adds no parsing or formatting detail for the nested variants object beyond what the schema example provides, so 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 ('Slice several setting variants in parallel in one call and compare them') with the exact comparison dimensions enumerated. It is immediately distinguishable from slice_model (single slice) and optimize (ready-made goals) without reading the schemas.

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 names both alternatives and the conditions that select them: 'use optimize for the 5 ready-made goals and slice_model for a single slice', contrasted with 'use it to test your own settings'. Nothing is left to inference.

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 readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false. The description is consistent with those and adds useful behavioral context about detecting first-use setup and the required follow-up flow, though it does not elaborate on error behavior or response details.

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 front-load what the tool returns and follow with the key session-start workflow. Every sentence carries useful information, and there is no repetition beyond the brief read-only confirmation.

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, read-only info tool with no output schema, the description sufficiently explains the returned status fields and the conditional setup workflow. An agent has enough context to call it first and know what to do if setup_needed is true.

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 has zero parameters, so there is no parameter semantics to clarify. The baseline for a no-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: return the connector's status. It enumerates the status contents (setup_needed, saved defaults, Bambu Studio and preset paths, output folder, printer configured) and connects to the sibling setup_defaults, so an agent can distinguish it from tools like printer_status or list_presets.

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 clear usage guidance: call it first in a session, then if setup_needed is true ask the user for printer/build plate/filament and call setup_defaults. The next-step routing is explicit, though it does not state when not to use the tool.

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 non-read-only, idempotent, non-destructive, but the description adds the crucial nuance that the source is modified only when output_path points at it, and that no slicing occurs. It doesn't cover failure modes (invalid settings keys, missing file) or what the tool reports back, which keeps it short of 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?

Two sentences, zero filler, with the scope constraint front-loaded before the alternative-tool routing. Every clause carries decision-relevant 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 covers the mutation semantics, the no-slicing behavior, and the original-file safety rule, which is nearly everything an agent needs. A minor gap remains around the return value (e.g. the written path) and error behavior, but the core contract is complete.

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%: path, settings format, default output naming, and the replacement caveat are all documented in the schema. The description reinforces the settings-editing intent and the output_path overwrite risk but adds no syntax or format detail beyond what the schema already states, 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 ("Write a copy of a 3MF project with changed settings, without slicing") and immediately frames the exact scope: the original stays untouched. That scope statement separates it cleanly from the slicing siblings without the agent opening any 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?

Explicitly names the intended use ("hand the user an edited project") and the alternative path for a different goal ("to measure the effect of settings, use slice_model or compare_slices instead"). It even gives the reason the alternatives are preferred (they never modify the original), which is exactly the when/when-not guidance an agent needs.

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 safety profile is covered; the description adds the source file inside the archive, the return type ('as Bambu strings'), and a concrete failure mode ('Fails on a 3MF without Bambu settings'). It stops short of describing output structure or how missing keys behave under a filter.

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 short sentences: what it reads, the safety/format note, then disambiguation and failure mode. Front-loaded and 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 still signals the return type (Bambu setting strings) and the error condition, which is the key operational fact for a read-only lookup. Minor gap: it doesn't say what the filtered result looks like when nothing matches.

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 100% and both parameters (path, key_filter) are documented there, including an example. The description adds no parameter-level detail beyond what the schema already provides, 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 ('Read the print settings stored in a Bambu 3MF project (project_settings.config)') and explicitly distinguishes itself from inspect_3mf (summary) and check_settings (problems). An agent can pick it 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?

Gives the selecting condition ('see the values a project will print with') and names both alternatives with their distinct roles. Nothing is left to inference about when to choose this tool.

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 readOnlyHint/idempotentHint/destructiveHint=false, so safety is covered. The description still adds real context beyond them: inheritance is resolved before return, values are Bambu-format strings, and behavior on an unknown name (error plus close-name suggestions) is disclosed. It stops short of describing output shape or size, but that is a minor gap.

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 short sentences, front-loaded with what it returns, then sibling routing, then failure behavior. "Read-only" is mildly redundant with annotations but costs almost nothing and the rest is waste-free.

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-param read tool with full schema coverage and no output schema, the description covers scope, value format, resolution behavior and error handling. Only the concrete shape of the returned setting collection is left implicit, which keeps it just below a 5.

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 100% with enum and per-parameter descriptions, so the schema does the heavy lifting. The description's mention of resolved inheritance loosely relates to only_overrides but does not explain key_filter or the override semantics beyond what the schema already states, so 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?

Specific verb+resource: "Read the settings of one preset" with the key qualifier that inheritance is resolved and values are Bambu strings. It explicitly distinguishes itself from compare_presets and get_3mf_settings, so an agent can route between the three without opening schemas.

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 an explicit positive case (inspect a single preset) and names two alternatives with the conditions that select them: compare_presets for diffs only, get_3mf_settings for 3MF-stored settings. Prerequisite naming also points to list_presets for valid names.

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 readOnlyHint, idempotentHint and destructiveHint=false, so 'Read-only' adds nothing new. What does add value is the disclosure that output varies by file — full Bambu project vs geometry only, and slicing results only 'if it has any' — which prepares the agent for conditional fields. It stops short of describing failure modes for malformed or non-3MF files.

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, each earning its place: what it returns, its safety profile, and its routing role. The routing instruction is front-loaded after the output summary, and there is no filler.

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 compensates by enumerating the summary's contents, and the single-parameter schema is fully documented. An agent knows what it will get, when to call it first, and where to go next.

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 a single parameter with 100% schema description coverage ('Absolute path of a .3mf file'), so the schema already carries the semantics. The description adds no path format, extension, or permission detail beyond it — 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?

Specific verb 'Summarize' plus resource '3MF file', with an enumeration of exactly what is reported (project vs geometry-only, printer/presets, objects and their settings, plates, slicing results). It also explicitly distinguishes itself from get_3mf_settings and analyze_model, so an agent can pick it without opening either 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?

'Use it first on any 3MF' gives an explicit entry-point rule, and the sentence names two alternatives with the conditions that select them: get_3mf_settings for the full project settings list, analyze_model for geometry. Both when-to-use and when-to-use-something-else are covered.

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 readOnlyHint, idempotentHint and destructiveHint=false, so the "Read-only" sentence restates structured data. The only added context is that results carry source and parent, which is return-value information the output schema already covers; nothing is said about result size or ordering.

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 filler, with the scope constraint front-loaded before the routing to alternatives.

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 annotations covering safety, an output schema covering returns, and full parameter documentation, the description supplies what is needed to select and call the tool. Minor gaps such as result ordering or limits are not essential to invocation.

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% with two enums, so the schema fully documents kind, search, source and printer_name. The description adds no syntax or default behavior beyond that, 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 ("List Bambu Studio presets of one type") plus the returned fields (source and parent), and explicitly marks it read-only. It is clearly distinguishable from get_preset, which fetches a single preset.

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?

Names the downstream tools this enables (get_preset, compare_presets, slicing) and the condition to use it (finding an exact preset name). It also names an alternative, material_guide, and the situation that selects it.

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 read-only/idempotent/non-destructive, and the description's "Read-only" merely mirrors that. It does add real context beyond the annotations: the advice is scoped to the default printer, and it discloses the shape of the returned guidance (plates, temps, enclosure, AMS, drying), which matters since there is no output 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?

Front-loads purpose in the first clause, then the returned-content list, then the usage routing. Dense and mostly waste-free, though the enumeration of advice categories is slightly list-heavy for a two-parameter tool.

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 carries the return-value burden and does so by naming every category of advice returned. It also flags the default-printer scope, which conditions the results. Nothing needed to invoke 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 100%, so both parameters are already documented in detail, including the "Omit to list the materials" behavior. The description adds the downstream use of the filament parameter (it is the preset passed to slicing tools), but no syntax or format guidance beyond the schema. 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 ("Give printing advice for a material") and enumerates exactly what the advice covers: filament preset, build plates, temperatures, enclosure, AMS, nozzle, drying. It is clearly distinguishable from siblings like list_presets or get_preset, which the description names.

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 gives when-to-use ("pick the filament preset passed to slicing tools") and routes the alternative case to list_presets for brand searches. The choice between this tool and its closest sibling is fully resolved in the description.

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 non-destructive, idempotent, closed-world behavior, and the description adds valuable context beyond that: slicing runs in parallel, accelerations are clamped to printer limits, the original file is never modified, and output lands under output/. It does not address timing or failure behavior, keeping it short of 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?

Front-loaded with the verb and scope, and every sentence carries routing or behavioral information. The opening clause is slightly run-on with the parenthetical goal list, but nothing is wasted.

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 8 parameters and no output schema, the description adequately covers what the tool produces and where, plus the key non-obvious input (filaments). Less complete on how the comparison is presented or what happens on multi-plate slicing, but sufficient to invoke 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?

Schema coverage is 100%, so baseline is 3, but the description adds real guidance the schema lacks — that `filaments` should carry the user's chosen preset — and clarifies the relationship between `goal` and the parallel comparison. Minor extra value over the already-thorough schema.

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 (slice in parallel) and the full resource scope (original + five ready-made goal recipes), and says exactly what is returned (comparison, recommended goal variant, result.3mf). It is clearly distinguishable from compare_slices, which is named 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?

Gives an explicit usage trigger ("how should I print this"), a concrete input instruction (pass the user's chosen filament preset in `filaments`), and names the alternative with its condition (compare_slices for custom settings). No inference required.

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?

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=true) by listing the automatic decisions taken, the artifacts produced (result.3mf under output/), and the returned time, weight, decisions and warnings. It stops short of noting runtime cost of slicing or whether a re-run overwrites prior outputs, which is what keeps it off 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?

Front-loaded with the core transformation, then the pipeline list, then the output and the sibling routing — a sensible order with little waste. Minor blemishes: the run-on enumeration and a missing space in "result.3mf" slightly hurt readability.

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 carries the return-value burden itself and does so (time, weight, decisions, warnings, the result.3mf path). Combined with the alternative routing and default-behavior notes, an agent has everything needed to call it and interpret the result.

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 schema already documents all nine parameters, including enum meanings for goal, supports and orientation. The description adds a pipeline narrative that maps loosely onto copies/supports/orientation/bed_type, but it adds no new per-parameter meaning — notably it never explains the filament-overrides-material precedence that the schema hints at.

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 concrete verb and resource (turn an STL/geometry-only 3MF into a print-ready Bambu project) and enumerates exactly what the pipeline does: analysis, orientation, material presets, plate, supports/brim, copies, slice. It also explicitly disambiguates from siblings by naming optimize and slice_model for complete Bambu projects, so an agent can route without opening a 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?

Gives both the when (raw models) and the when-not with named alternatives ("for a complete Bambu project use optimize or slice_model instead"). That is an explicit routing rule rather than an implied one.

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/destructive/idempotent, but the description adds real context beyond them: the transport (local MQTT), the guarantee that it never sends commands, and the two concrete failure modes (missing credentials, printer powered off). A small credit deduction only because it says nothing about latency or how the live snapshot is timed.

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: what it reads and how, the read-only guarantee, then prerequisites and failure modes. Purpose is front-loaded and every clause carries information an agent needs before calling.

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 compensates by listing exactly what the response contains (job state, temps, fans, AMS, HMS errors). Combined with the documented prerequisites and failure conditions, an agent has everything needed to invoke it correctly or to decide it cannot.

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 single optional 'include_raw' parameter is fully documented in the schema (100% coverage), so the schema carries the semantics. The description never mentions it, adding no meaning beyond the structured field — 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 ('Read the printer's live status over the local network (MQTT)') and then enumerates the data returned: job progress, temperatures, fans, AMS trays, filaments, HMS errors. None of the sibling tools (3MF/preset/slicing) overlap, so an agent can immediately tell this is the hardware-state tool.

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 concrete preconditions and failure conditions: host, serial and access code must be in config.json, and it fails if they are missing or the printer is off, with a pointer to connector_info for that setup. It omits an explicit 'do not use when...' clause, but there is no competing status tool among the siblings, so the gap is minor.

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?

Beyond annotations (destructive=true, idempotent=true), it explains that an existing preset of that name is overwritten, that the previous file is backed up in backups/ first, and that Bambu Studio must be restarted to see the change. This adds real behavioral context about destructiveness and recovery.

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?

Four short sentences, each doing distinct work: purpose, overwrite/backup behavior, call precondition, and restart requirement. The important scoping and safety facts are 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 destructive mutation tool with no output schema, the description covers what is overwritten, how the prior state is preserved, when it is safe to call, and what the user must do afterward. Annotations plus this text give the agent enough 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?

Schema description coverage is 100%, so the schema already documents kind, name, parent, and settings. The description does not add parameter-level detail beyond what the schema provides, such as parent inheritance behavior or settings syntax.

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: 'Create or update a user preset in Bambu Studio's user folder.' It is clear which operation is performed, though it does not explicitly contrast itself with sibling tools like compare_presets or get_preset.

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 an explicit precondition: 'Only call it once the user has agreed to the changes, after slicing to compare them (compare_slices).' This tells the agent both when to invoke it and which sibling tool to use first, plus a post-call restart requirement.

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 annotations already declaring non-destructive, idempotent behavior, the description adds useful context: storage in config.json, validation of provided values, and saving only the values given. It stops short of describing error behavior or the exact return shape beyond current values and available choices.

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 purpose and immediately followed by the no-argument/argument behavior and trigger conditions. No wasted text.

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?

Complete enough for a three-optional-parameter, dual-mode tool with full schema coverage and no output schema. The description covers first-use triggering, validation, partial saves and what the no-argument call returns, though it could say more about failure handling.

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 schema already carries parameter examples and meanings. The description adds meaningful semantics by stating that supplied values are validated and only those given are saved, implying partial updates for the optional machine, bed_type and filament parameters.

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 dual-purpose verb and resource: read or save the user's default printer, build plate and filament. It is clear what the tool operates on, though it does not explicitly differentiate itself from siblings such as save_preset or get_preset.

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 clear usage contexts: call on first use via connector_info.setup_needed, or when the user changes printer, plate or usual filament. It also explains the no-argument versus argument behavior. It does not name alternatives or state when not to use it.

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 readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful context such as newest-first ordering and returned fields, but it does not disclose pagination behavior or other operational details beyond what annotations and the output schema provide.

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 compact sentences with the core purpose and use case front-loaded. Every clause contributes information about ordering, returned fields, safety, or usage, with no waste.

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, complete parameter descriptions, and annotations covering safety, the description is nearly complete for this tool. It could mention the search and limit behavior explicitly, but those are already well covered by 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%, so both the limit and search parameters are already documented in the schema. The description does not add parameter-specific meaning beyond what the schema provides, which is the baseline expectation at full coverage.

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: list previous slices, with scope ('newest first'), returned fields, and a use case. It clearly distinguishes itself from slice_model by saying to use it to find an earlier result instead of slicing anew.

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 explicit guidance: use this to find an earlier result again instead of slicing anew, naming the alternative behavior. It does not explicitly state exclusions or compare against sibling tools like compare_slices, but the usage context is 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?

Adds substantial context beyond the annotations: the result.3mf is written under output/, originals are never modified, and an identical slice is served from cache. Those details explain why readOnlyHint=false coexists with destructiveHint=false and idempotentHint=true. It stops short of noting runtime cost or how cache identity is determined.

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 action and its outputs before side effects and sibling routing; three sentences, no filler. Minor cost: dense packing and awkward rendering ('result.3mf' with a missing space) briefly slow parsing.

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 10-parameter tool with no output schema, it covers everything an agent needs: return values ($-described inline), file side effects, caching, and how preset omission is resolved. Nothing material is left to inference.

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 100%, so baseline is 3, but the description earns credit by explaining preset resolution: a Bambu 3MF keeps its own settings and is moved to the default printer if made for another, while an STL takes machine/process/filaments or the user's defaults. That is meaning the schema only gestures at.

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 concrete verb and resource ('slice once with the real Bambu Studio engine') and enumerates what comes back: print time, filament weight, per-line-type time, warnings, and the result .3mf path. That output list makes it immediately distinguishable from siblings like compare_slices or prepare_print.

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 to alternatives with the condition that selects each: compare_slices for trying several settings at once, optimize for ready-made goals, prepare_print for raw STL to project. It also explains input-dependent behavior (3MF keeps own settings vs STL needs machine/process/filaments), so the caller knows which path applies.

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