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

No annotations are provided, so the description carries the full behavioral burden. It only states that the tool mutates an existing scene via the GDScript engine, but does not disclose side effects such as whether the scene file is saved, whether the editor must be running, whether changes are reversible, or what happens on failure.

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 a short, scoped sentence followed by a compact parameter list. Every parameter earns its place and the list format is well suited to an agent scanning for argument meanings.

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?

Parameters are well covered and an output schema exists, so return-value details are not required. However, for a mutating tool with no annotations, the description is incomplete about preconditions, side effects, and error behavior, which an agent would need to use it safely in a real project.

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%, but the description fully compensates by documenting all six parameters. It adds meaningful context: absolute vs relative paths, default parent, optional properties dictionary, and an example node type. This gives an agent enough semantic grounding to populate the arguments correctly.

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 clearly states a specific action ('Add a node') and resource ('existing Godot scene'), which distinguishes it from scene creation or loading tools. It does not explicitly name sibling alternatives, but the 'existing' qualifier gives enough context to route correctly.

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 context is implied by the resource description: this is for adding a node to an existing scene rather than creating or saving a scene. However, it does not explicitly state when to prefer this tool over siblings like create_scene or save_scene, nor any preconditions such as needing the scene open.

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 provided, the description carries the full behavioral burdenと思われる。 It discloses that the tool writes files unless dry_run is used, that dry_run 'report[s] changes without writing files,' and that recursive controls subdirectory scanning. This is meaningful transparency for a bulk mutation operation, though it does not discuss reversibility or file-matching edge cases.

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 focused and front-loaded: purpose first, then a compact param mapping example, then an Args list that covers all four parameters. Every sentence contributes either the outcome, the data format, or a parameter semantic.

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 bulk-mutation tool with no annotations)Skip? The description covers the key inputs, the file type, recursion, and the no-write dry-run path. It does not specify path resolution details or error-handling behavior, but since an output schema existsasi, return-value documentation is not required here. The core information needed to invoke it correctly is present.

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 fully compensate. It does: directory is defined as where to scan, uniform_overrides is explicitly mapped with a concrete Python-dict example, recursive states its default and behavior, and dry_run semantics are stated. This adds real meaning the bare schema lacks.

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 names a specific action ('Scan ShaderMaterial .tres files and bulk-override shader_parameter/* values') and resource, and gives concrete examples ('cell-shading threshold, outline thickness, ink color'). It clearly distinguishes itself from the animation, texture, and scene siblings by targeting shader uniforms across many assets.

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 states the intended use case: batch-updating a uniform parameter across hundreds of assets in one call, with recursive scanning and a dry-run mode. It does not explicitly name alternative tools or exclusion criteria, but the bulk-vs-single-asset context is clear from the wording.

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 must carry the full behavioral burden. It discloses that it writes an Animation resource block and toggles Camera3D.current at specified timestamps, and details the switch dict fields. However, it does not state whether the scene file is modified and saved, what happens to existing animations, or how errors (e.g., invalid NodePath) are handled. These are meaningful gaps for a mutation 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?

The description is concise and logically structured: it leads with purpose, then explains the switch dict format, then lists args. It is not bloated, though the arg list could be tightened. Overall, it earns its space.

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?

Given the tool's moderate complexity (5 params, 3 required) and the presence of an output schema, the description covers all inputs and the switch structure adequately. It does not discuss edge cases or return values, but these are partially covered by the output schema. The description is sufficient for an agent to call the tool correctly in typical scenarios.

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 schema has 0% description coverage, so the description fully compensates by explaining each parameter: scene_path is an absolute .tscn path, anim_player_node is the AnimationPlayer node name, switches is a list of dicts with required keys, animation_name is the clip name, and timeline_length is total length. This is significantly more than the schema provides.

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 ('Write an Animation resource block'), the resource (Camera3D.current toggling), and the purpose (multi-angle cinematic cuts). It clearly distinguishes itself from sibling tools like generate_bezier_camera_path or inject_lookat_tracking, which handle different aspects of camera animation.

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 the purpose but no guidance on when to choose this over alternatives. It does not mention exclusions or when to prefer a sibling like generate_state_machine or stitch_animation_library. An agent would have to infer usage from the name and purpose, which is insufficient.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It says 'Compute and inject', implying a mutation, but does not disclose whether the scene file is modified in-place, whether it creates or updates an existing node, what happens if the scene is missing or the node name conflicts, or any side effects on existing blend spaces. There is no mention of reversibility, permissions, or error behavior. This is a significant gap for a tool that modifies scene 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?

The description is well-structured and front-loaded: the purpose is stated first, followed by blend point requirements, then an Args list. It is concise, with no filler sentences. The Args section is formatted for readability. It earns a 4 for efficiency and clarity of structure.

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?

The tool is complex: it injects an AnimationNodeBlendSpace2D into a scene file, requiring prerequisites like an existing scene file, AnimationPlayer, and animation clips. The description does not mention these prerequisites, side effects, or what happens on invalid inputs. It also does not state whether it replaces an existing blend space or how it integrates with the AnimationTree. With no annotations and no output schema shown, the description is incomplete for safe usage.

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 explains the structure of blend_points in detail (animation and position fields with examples), and gives a one-line description for each parameter in the Args section. However, it does not explain the semantics of node_name (e.g., whether it replaces an existing node), the expected format of scene_path, or the meaning of axis labels beyond being labels. It adds value over the bare schema but does not fully compensate for the lack of schema descriptions on all 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 verb ('Compute and inject'), a specific resource (AnimationNodeBlendSpace2D), and the use case (directional locomotion blending N/S/E/W + idle). This clearly distinguishes it from sibling tools like generate_state_machine or compile_state_transitions, which target different animation structures. The purpose is unambiguous.

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 usage for directional locomotion blending, but it does not explicitly state when to choose this tool over alternatives or list exclusions. There is no mention of when not to use it, such as for state machines or other blend types. The context is inferable from the description, but not made explicit, so it earns a 3.

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. It discloses meaningful details: required transition dict keys, optional condition, xfade_time default, and advance_mode semantics. However, it does not state whether existing transitions are replaced or appended, what validation occurs, or what side effects writing to the .tscn file has.

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 scannable and front-loaded, with a clear one-line purpose followed by compact bullet lists for transition fields and arguments. Every sentence adds useful information 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?

The description is largely sufficient for invoking the tool correctly: it defines all parameters and the nested transition contract. It falls slightly short by not explaining whether the transition list replaces or merges with existing transitions, and by not stating that the state machine must already exist in the scene.

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%, and the description fully compensates. It explains each argument: scene_path is an absolute .tscn path, state_machine_resource_id is the sub-resource id, and transitions is a list of dicts with all expected keys, defaults, and value meanings.

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 clearly names the operation ('Write transition arrow connections') and the target resource (AnimationNodeStateMachine via scene_path and state_machine_resource_id). It is specific enough to be distinguished from sibling tools like generate_state_machine, though it does not explicitly state that distinction.

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 explains what the tool does and the required data shape, but it gives no guidance about when to use it versus alternatives. There is no mention of prerequisites such as a previously generated state machine, nor any exclusion such as 'use generate_state_machine to create the machine first'.

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 must fully disclose behavioral traits. It mentions creating a file, but it does not state whether an existing file is overwritten, whether intermediate directories are created, whether the project must already exist, or what happens on invalid inputs. The output schema exists, so return-value details are covered, but side effects and failure modes are left undisclosed.

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 compact and front-loaded. The main purpose is stated in one sentence, followed by a clean Args list. Every line provides needed information, and there is no filler or repetition of schema titles.

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 creation tool with a straightforward parameter list, the description covers the essential invocation details. However, it lacks side-effect context, error behavior, and guidance about when to prefer this tool over siblings. These gaps keep it from being fully complete, though the output schema likely covers return values.

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 is the only source of parameter meaning. It compensates fully by explaining project_path as an absolute path, scene_path as a project-relative path with an example, and root_node_type as a Godot class name with a default. This adds substantial semantic value beyond the bare input 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?

The description clearly names the operation: 'Create a new Godot scene file via the GDScript engine.' It identifies the resource (a scene file) and the action (create). It does not explicitly differentiate itself from sibling tools like save_scene, but the word 'new' helps conceptually separate creation from saving an existing scene.

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?

There is no guidance about when to use this tool instead of alternatives. Sibling tools like save_scene, add_node, or launch_editor are not mentioned, and no context is given about whether this tool is appropriate for new projects, existing scenes, or modifications. The description simply states what it does without helping an agent decide between related tools.

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?

No annotations are provided, so the description carries the full burden. It discloses the operation (export) and the optional filtering behavior (mesh_item_names), but it does not state whether the output file is overwritten, whether the scene must be saved first, whether the export is destructive to existing files, or what happens if the scene contains no meshes. For a file-writing tool, this is a meaningful 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?

The description is compact and front-loaded with the core purpose, followed by a clear Args list. Every sentence earns its place. The Args block is slightly redundant with the schema but serves as inline documentation given 0% schema coverage, so it is justified.

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?

The tool has an output schema, so return values are presumably covered. The description covers the main inputs and the optional filter. However, it lacks context about prerequisites (e.g., scene must exist, project must be open), overwrite behavior, and error conditions. For a file-export tool with no annotations, this is a moderate 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 description coverage is 0%, so the description must compensate. It does explain each parameter's role in the Args block, including the optional mesh_item_names behavior. However, it does not add details like path format expectations (e.g., trailing slashes, .tscn extension) or how mesh_item_names maps to node names. The description adds basic meaning but not deep 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?

The description states a specific verb ('Export'), a specific resource ('3D scene as a MeshLibrary .res resource for GridMap'), and the target format. It clearly distinguishes this from sibling tools like create_scene or save_scene, which handle scene files rather than exporting a mesh library resource.

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 when to use it: when you need a MeshLibrary .res for GridMap from a .tscn scene. It does not explicitly state when not to use it or name alternatives, but the purpose is specific enough that an agent can infer the context. No explicit exclusions or alternative routing are provided.

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?

No annotations are provided, so the description must carry the full behavioral burden. It clearly states that the tool writes to a .tscn file and adds Path3D/Curve3D nodes, which is the core behavior. However, it doesn't disclose potential side effects like overwriting existing nodes, whether the file must already exist, or if any permissions are required. The description covers the primary action but leaves important edge cases unstated.

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 well-structured and front-loaded. It starts with a concise summary of the tool's purpose, then specifies the waypoint dict format, and then lists each argument with clear explanations. Every sentence adds value; there is no filler or repetition. The length is appropriate for the complexity of the 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?

For a tool with six parameters and nested waypoint structures, the description covers the essentials: parameter meanings, defaults, and even tension usage guidance. An output schema exists, so return values are handled externally. Minor gaps include whether the scene file must pre-exist or what happens if nodes with the same name already exist, but these are edge cases that don't impede correct invocation in most scenarios.

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 schema has zero description coverage, so the description is the only source of parameter meaning. It explains every parameter: scene_path (absolute path), path_node_name (naming example), waypoints (with required 'position' and optional 'tilt' fields), add_path_follow, add_camera, and tension (with range -1.0 to 1.0 and usage guidance for sweeping vs. tight moves). This fully compensates for the missing schema descriptions.

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 opens with a precise statement: 'Calculate Catmull-Rom bezier handles from world-space waypoints and serialize them as Path3D + Curve3D node blocks in a .tscn file.' This gives a specific verb, resource, and output format. It also lists supported moves (arc pans, dolly zooms, etc.), which clarifies the tool's scope and differentiates it from generic scene manipulation tools, though it doesn't explicitly name sibling tools. The purpose is unmistakable.

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 usage context by describing the supported camera moves and the nature of the output, but it never explicitly tells the agent when to choose this tool over alternatives like build_camera_switcher_timeline or inject_lookat_tracking. There is no 'use this instead of X' guidance, so the usage is implied rather than explicit.

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 provided, the description must carry the behavioral disclosure burden. It indicates the tool modifies a .tscn file ('inject'), but does not detail side effects like overwriting existing nodes, file backup, or failure behavior. It also doesn't mention permissions or whether the operation is reversible. This is a partial disclosure, not fully transparent.

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 structured with a summary line, a bullet list of state dict requirements, and an Args list. It is a bit verbose but every part serves a purpose. The core purpose is front-loaded, and the parameter details are organized clearly.

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?

Given the tool has 5 parameters and an output schema, the description covers all parameters with practical examples and explains the expected input format for the states list. It doesn't describe return values, but the output schema exists, so that is not required. For a mutation tool on scene files, it is reasonably complete, though it could mention error conditions or idempotency.

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 schema has zero descriptions for parameters, so the description compensates by explaining each argument in the Args section, including the required fields for each state dict (name, animation, position). It also clarifies the default behavior of start_state ('defaults to first state'), which is not evident from the schema's empty default. This adds meaningful guidance 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?

The description states a specific action ('Inject an AnimationNodeStateMachine sub-resource block'), the target resource type, and the file type (.tscn). It clearly distinguishes this from sibling tools like create_scene or add_node by focusing on state machine generation.

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 says 'define visual state blocks without opening the editor', which implies when to use it. It does not explicitly list exclusions or alternative tools, but the purpose is specific enough that an agent can infer this is for state machine creation, not general scene editing.

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?

No annotations are provided, so the description carries the full burden. It states that it generates GDScript and resource text and notes that scene_path is 'appended if exists,' hinting at file-system interaction, but it never clarifies whether the tool writes to disk, overwrites files, or returns output only. The phrase 'appended if exists' is ambiguous.

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 summary sentence is front-loaded and specific, and the Args block is compact. It is slightly less tight because blend_node_name's explanation largely restates the parameter name, but overall there is little 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?

There is an output schema, so return format does not need to be described, and the core generation behavior is explained. However, the lack of side-effect clarity, the ambiguous scene_path behavior, and the absence of usage guidance leave meaningful gaps for a tool that receives a file path and has no annotations.

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 0% schema description coverage, the Args block provides crucial semantics for all three parameters: scene_path is an absolute .tscn path, locked_bone_paths are Bone NodePaths with an example, and blend_node_name names the node. The scene_path explanation is somewhat ambiguous ('appended if exists') but still adds meaning beyond the bare 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?

The description opens with 'Track Filtering & Blending' and the verb 'Generate' plus a specific resource (AnimationNodeBlendFilter). It explains the exact purpose—locking bone chains while upper-body bones follow an overlay—which distinguishes it from the many animation-generation 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?

The use case is implied by the explanation of locking specific bone chains against an overlay animation, so an agent can infer when this is relevant. However, there is no explicit statement of when to prefer this over sibling animation tools or 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?

No annotations are present, so the description carries the full burden. It states that this retrieves current stdout/stderr, but it does not disclose whether the buffer is cumulative, cleared, capped, or what happens when no project is running.

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 a single focused sentence with no filler. 'Current stdout/stderr' is specific, and nothing needed for basic invocation is missing.

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 tool with an output schema, this is nearly complete. The main implicit requirement is that a project must be running, which is reasonably conveyed by 'from the running Godot project.'

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 are zero parameters and the schema already covers this fully. The description adds useful context about what resource is being read, and there are no parameter semantics to clarify.

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 opens with a specific verb and object: 'Retrieve current stdout/stderr.' It clearly identifies a read-only debug operation and distinguishes it from sibling tools like run_project, stop_project, and launch_editor.

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 phrase 'from the running Godot project' gives clear context for when this tool applies. It does not explicitly name alternatives or exclusions, but the intended use is obvious enough among the sibling tools.

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?

No annotations are provided, so the description carries the behavioral burden. The word 'Return' implies a read-only query with no mutation, but the description does not explicitly state side-effect-free behavior, error conditions, or environment dependence.

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?

A single sentence with no wasted words. The key information is front-loaded and sufficient for a zero-parameter utility.

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 no-argument getter with an output schema, the description is complete. An agent knows exactly what the tool does and what it returns; nothing necessary for correct invocation 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?

The tool has zero parameters, so the schema is fully complete. The description adds the only meaningful semantic detail: the returned value is the Godot 4 version string.

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 uses a specific verb ('Return') and a precise resource ('the installed Godot 4 version string'). It is clearly distinct from sibling tools, none of which is a version lookup utility.

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 context is clear: use this tool to retrieve the installed Godot 4 version. There are no closely related alternatives to exclude, though the description does not explicitly state when not to use it or name alternatives.

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. It states the tool 'returns metadata,' implying a read-only operation with no side effects, but it does not explicitly disclose non-destructive behavior, error handling on invalid paths, or any permissions required. It adds minimal behavioral context beyond the function name.

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 a single direct sentence followed by an Args block with one parameter. No filler; front-loaded with the core purpose.

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?

The tool has one parameter, an output schema exists (so return values are documented), and the description clarifies the parameter's semantics. It is complete for an agent to invoke correctly, though it omits edge-case behavior (invalid paths) which might be covered by the output 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 0%, and the description compensates by specifying that project_path is 'Absolute path to the Godot project directory,' adding meaning the schema lacks (absolute required, points to directory). It does not elaborate on path validation or file requirements, but it gives the key semantic.

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 ('Return') and resource ('metadata about a Godot project'), enumerating the kind of metadata (name, structure, Godot version). This distinguishes it from siblings like get_godot_version (which likely returns the editor version) and list_projects (which likely returns paths).

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?

No explicit when-to-use or alternative routing is given. The intended usage is implied by the name and description, but the description does not contrast with siblings like list_projects or get_godot_version, nor does it state any conditions under which another tool should be chosen.

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?

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the action and parameters, but does not disclose side effects (though likely non-destructive), error handling for invalid paths or missing UIDs, or any output format details. The description is too sparse to convey expected behavior beyond the basic operation.

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 concise and front-loaded with the purpose statement, followed by parameter details. Each sentence earns its place; there is no fluff. The structure is logical: purpose first, then parameter guidance. It could be improved by adding a brief note on expected output or error conditions, but as written it is appropriately sized.

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?

The tool is a simple getter with an output schema (though not shown in the prompt, the context indicates one exists), which lessens the need to describe return values. However, the description lacks information on failure modes (e.g., what happens if the file doesn't exist, if the project path is invalid, or if the resource has no UID). For a tool with only two parameters and a straightforward purpose, this is borderline adequate but leaves gaps that an agent might encounter.

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 schema provides zero descriptions for parameters (0% coverage), so the description must compensate. It does so by adding meaningful semantic context: 'Absolute path to the Godot project directory' and 'File path relative to project'. This clarifies the required format and relationship between the two parameters, which is exactly what an agent needs to construct a valid call. However, it doesn't specify edge cases like path normalization or validation, so it's not a full 5.

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 action ('Get the UID') and a specific resource type ('Godot 4.4+ resource file'). It clearly differentiates from sibling update_project_uids by focusing on retrieval rather than modification. The verb-resource pairing is clear and unambiguous.

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 usage when you need a UID, but it does not explicitly state when to prefer this tool over alternatives or mention any exclusions (e.g., files that don't have UIDs). It provides the context of needing a UID but lacks explicit routing guidance, though the sibling name update_project_uids makes the distinction inferable.

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 readOnlyHint or destructiveHint annotations, the description carries the full burden of revealing side effects. It states that it writes a .gd file, but does not disclose whether it mutates the .tscn scene, attaches the script to the Camera3D, or overwrites existing files. For an 'inject' tool, this is a significant transparency 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?

The purpose is front-loaded in a single sentence, and the parameter list is compact with no filler. Every line contributes either invocation guidance or factual detail about arguments.

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 documentation is not the main gap. However, the description omits prerequisites such as the scene and nodes needing to exist, and side-effect behavior such as whether the scene is saved or existing scripts are overwritten. These are important for a file-writing, scene-injecting 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?

The Args block defines all four parameters with functional meaning absent from the schema, including absolute scene path, NodePath purpose, target example, and the empty-string default for script_output_path. This compensates well for the 0% schema description coverage, though NodePath syntax details are left to convention.

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 names a concrete deliverable (a GDScript) and the mechanism (procedural transform tracking with slerp interpolation), so an agent can understand what the tool produces. It is reasonably distinct from camera and animation siblings, though it does not explicitly contrast with similar tools like generate_bezier_camera_path.

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?

There is no explicit statement of when to use this tool versus alternatives such as generate_bezier_camera_path, build_camera_switcher_timeline, or generate_track_filter. The only usage context is implicit in the summary, and no exclusions or alternative routing are provided.

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?

No annotations are provided, so the description carries the behavioral disclosure burden. It does disclose one important behavior: the launch is non-blockingabb. However, it does not mention error behavior, whether the command returns immediately, or any side effects beyond launching the editor. This is partially informative but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one sentence plus a single argument explanation. It is tightly written, front-loads the core action, and contains no filler or repeated schema 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?

For a tool with a single simple parameter and an output schema present, the description covers the key operational detail (non-blocking) and the required input. It is sufficient for an agent to invoke it correctly, though it could benefit from noting what the output contains or what happens when the project path is invalid.

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 input schema provides only the parameter name and type with 0% schema description coverage, so the description must explain the parameter. It does: 'absolute path to the Godot project directory.' This adds meaningful semantics beyond the raw schema, though it lacks examples or validation details.

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 action ('Launch'), a specific resource ('the Godot editor'), and a specific argument ('given project'). It is clearly distinct from sibling tools like run_project, which runs a project rather than opening the editor, though it does not explicitly name another 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?

The description provides no guidance on when to use this tool versus alternatives. An agent is not told to prefer this over run_project, when non-blocking matters, or that this is for editing rather than executing. The only contextual clue is the word 'editor,' which is implicit rather than explicit.

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?

No annotations are present, so the description must carry the behavioral burden. The 'Find' wording signals a read-only search and the recursive flag describes traversal, but the description does not disclose potential costs of scanning large trees, detection criteria, or whether the search is local filesystem-only.

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 tight sentences followed by a compact Args block. Every sentence earns its place, and the main purpose is front-loaded before parameter details.

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 two-parameter discovery tool with an output schema, the essential call semantics are covered: what to search, where, and whether to recurse. It does not add sibling differentiation or edge-case behavior, but the supplied output schema and schema defaults fill most remaining gaps.

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%, yet the description fully compensates by defining both parameters: directory is 'Root directory to search' and recursive is 'If True, search all subdirectories.' This adds clear operational meaning beyond the bare schema property names.

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 opens with a specific directive, 'Find Godot projects under a directory,' which names the verb, resource, and search scope. This clearly sets it apart from sibling tools like launch_editor, run_project, or get_project_info, which concern execution or project details rather than discovery.

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 use case: call this when you need to locate Godot projects within a directory tree. However, it provides no explicit when-to-use guidance, no exclusions, and does not mention an alternative for inspecting a single project, so the usage context is only 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?

Annotations are absent, so the description carries the full burden of disclosing behavior. It only restates the semantic operation ('load') and does not disclose side effects such as whether the scene file is modified on disk, whether an existing texture is overwritten, or what happens on failure. This is a minimal operation description with no behavioral depth.

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?

A single purpose sentence followed by a compact argument list; every line earns its place. The argument explanations are front-loaded and avoid redundancy with 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?

All required inputs are covered and an output schema exists, so return values are not the main gap. However, as a mutation tool with no annotations, the lack of side-effect/persistence information leaves an agent uncertain whether calling save_scene is required after loading the texture.

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%, but the description compensates by explaining all four arguments with path conventions (absolute vs relative) and an example for node_path. Minor gaps remain, such as supported texture formats or whether scene_path must include a .tscn extension, but the core semantics are clear and actionable.

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 ('Load') and resource ('texture onto a Sprite2D/TextureRect node inside a scene'), which makes the tool's function immediately clear. It also distinguishes itself from sibling scene-authoring tools by naming the exact node types and the operation being performed.

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 use case is implied: apply a texture to an existing sprite node in a scene. However, there is no explicit when/when-not guidance, no mention of alternatives, and no prerequisites such as whether the scene must be open or saved before calling 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?

With no annotations, the description carries the full burden of behavioral disclosure, but it does not state whether the file is modified in-place, whether a backup is created, or whether the operation is reversible. It does usefully disclose that animation_name is currently a no-op, but the core mutation semantics are under-specified.

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 compact and front-loaded with the main action, followed by a focused Args breakdown. The 'Stepped Framerate Quantizer' label is slightly redundant with the next sentence, but overall every section is short and purposeful.

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?

The description covers all parameters and benefits from an output schema, so return value details are unnecessary. However, for a file-modifying tool with no annotations, the lack of explicit statement about in-place overwriting, backup behavior, or failure modes leaves an important gap for an agent deciding how to invoke it safely.

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 Args block is essential and does compensate: file_path is clarified as an absolute path, target_fps gets framerate examples and defaults, and animation_name is explicitly labeled as reserved. It could add more constraints or edge-case behavior, but the parameters are meaningfully explained.

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 clearly states a specific action and resource: rounding keyframe timestamps inside .tscn/.tres files to fixed frame intervals. The 12fps/24fps examples add concrete context and help distinguish it from sibling animation tools like set_animation_interpolation_mode.

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 provides clear context for when to use the tool: quantizing animation keyframes to a stepped framerate, with explicit anime/film examples. It does not explicitly name alternatives or exclusions, but the intended use case is clear enough.

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 provided, the description carries the full burden. It discloses that the tool alters file references (a mutation), but does not mention permissions, reversibility, side effects on existing references, or error behavior. It is not contradictory, but it is incomplete for a file-modifying operation.

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 efficiently structured with a purpose sentence, an example of the channel_map format, and an Args section. It is front-loaded with the core action and includes only necessary details, though the example could be slightly trimmed without loss.

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?

Given the complexity of editing a .tres file, the description covers the essential inputs and their semantics, but it does not address potential failure cases (e.g., missing file, invalid property names) or what the tool returns beyond an implicit success. The presence of an output schema helps, but the description alone is not fully self-contained.

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 explain parameters fully. It does: material_path is described as an absolute path, and channel_map is explained as a dict mapping property names to res:// paths, with a concrete example. This adds meaning beyond the bare schema and enables 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?

The description states a specific action: linking hand-painted textures into material property slots by altering ext_resource references in a .tres file. It clearly identifies the resource type and the mechanism, distinguishing it from sibling tools like load_sprite or batch_shader_uniforms without needing explicit contrast.

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 a use case (linking hand-painted textures) but does not explicitly state when to use this tool versus alternatives or any exclusions. It gives context but lacks direct routing guidance, which is a minor gap for an agent deciding between tools.

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 prose must carry the behavioral disclosure. It does disclose the headless mode, the Godot CLI mechanism, the timeout, and the structured log output. It stops short of stating whether any project files or .godot artifacts may be modified by the import validation, which is a meaningful gap for a no-annotation tool, but the general behavior is not hidden.

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 compact and front-loaded: a one-sentence purpose summary followed by a minimal Args legend. Every sentence contributes operational information, with no filler or repetition of the tool name.

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?

The description covers what the tool does, how it does it (Godot CLI), all parameter semantics, timeout behavior, and the output shape, and an output schema already exists for return details. It lacks explicit prerequisites/side-effect caveats, which prevents a perfect score.

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%, and the Args block compensates fully: it explains project_path requires an absolute path, enumerates the check values ('import', 'uids', 'shaders', 'all'), and gives effective defaults for checks and timeout_seconds. This adds operational meaning beyond the bare JSON schema properties.

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 opens with 'Headless Project Diagnostics' and a specific verb-resource statement: invoke the Godot CLI to validate imports, check UID linkages, and detect broken shader entry points. This clearly distinguishes it from sibling tools like launch_editor, run_project, or update_project_uids.

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 intended use is implied by the listed diagnostics (imports, UIDs, shaders) and the word 'headless', so an agent can infer when to reach for it. However, it never explicitly states when not to use it or names alternatives such as get_debug_output for runtime issues or update_project_uids for fixing UID problems.

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 burden of explaining behavior. It does disclose debug mode and output capture, which are useful behavioral traits, but it omits side effects such as whether the process remains running, whether output is returned immediately, or whether stop_project must be called afterward.

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 compact and front-loaded with the core purpose; the Args block is minimal and every line adds meaning beyond the schema. No filler or redundant restatement.

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 two-parameter tool with an output schema, the description covers the operation, mode, output behavior, and parameter semantics. It only lacks lifecycle context and sibling-tool routing, which keeps it slightly short of full completeness.

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?

Although schema description coverage is 0%, the description explains both parameters: project_path must be an absolute path, and scene is an optional specific scene file. This meaningfully adds beyond the bare schema, though the scene argument format could be more precise.

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 first sentence uses a specific verb ('Run') and resource ('Godot project'), plus the mode ('debug mode') and outcome ('capture output'). This clearly distinguishes it from sibling tools like launch_editor, get_debug_output, and stop_project.

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?

'Run a Godot project in debug mode and capture output' implies the intended use case, but the description never explicitly says when to choose this over launch_editor or get_debug_output, nor does it mention exclusions such as release-mode running.

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 must carry the burden of behavioral disclosure. It reveals that the tool writes a scene file and can use an alternate path, but does not say whether it overwrites existing files, whether the scene must already exist, whether directories are created, or whether the operation is reversible.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one purposeful sentence followed by a terse parameter list with no filler. The core behavior is front-loaded, and every line adds 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?

For a three-parameter file-writing tool, the description covers the invocation inputs but leaves open important context: whether saving is destructive/overwriting, whether the scene must already exist, and what the output indicates. The presence of an output schema reduces the need to document return values, but the missing mutation semantics keep this from being fully 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 0%, and the description compensates by explaining all three parameters: absolute project_path, relative scene_path, and conditional new_path. It stops short of specifying behavior like what happens when new_path is empty, but it adds meaning the schema lacks.

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, 'Save (or save-as) a Godot scene file', names a specific action and resource, and the save-as variant is explicit. This distinguishes it from siblings like create_scene and add_node without needing their 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?

No statement about when to choose this tool over alternatives such as create_scene or load_sprite. The parameter list implies a save workflow, but there are no conditions, exclusions, or explicit routing.

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 are absent, so the description carries the full burden of behavioral disclosure. It clearly implies in-place mutation of animation resource files, but it does not state whether the file is rewritten, whether the operation is reversible, what happens with invalid modes or track indices, or what the tool returns.

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 summary is front-loaded and the Args section is compact and well-organized. 'Interpolation Mode Swapper' is somewhat redundant with the tool name, but it does not waste meaningful space.

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?

All required input semantics are covered, and an output schema exists, so omitting return-value details is less critical. However, with no annotations, the description is incomplete around side effects, error behavior, and mutation guarantees, so it is only minimally complete for correct 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 0%, so the description must compensate, and it does. It explains all three parameters: file_path must be an absolute path, mode has named values with numeric aliases, and track_index uses -1 as a sentinel meaning 'all tracks'. This is substantially more informative than the bare input 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?

The description states a specific action ('Bulk-edit keyframe easing modes') and a specific resource ('.tscn/.tres file'), and enumerates the supported interpolation modes. It does not explicitly distinguish itself from sibling animation tools like quantize_animation_keyframes, but the focus on easing/interpolation modes is clear enough to identify the tool's purpose.

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?

No guidance is given about when to use this tool versus alternatives, or when not to use it. The phrase 'Bulk-edit' implies a batch use case and file types are stated, but an agent is not told how to choose this over sibling animation-related tools.

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?

No annotations are provided, so the description carries the transparency burden. It discloses the output artifact and the required clip dict shape, including the meaning of 'name' and 'path'. It does not mention overwrite behavior, validation failures, or side effects, leaving some behavioral gaps.

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 front-loaded with a clear one-line summary, followed by a compact list of required clip fields and an Args section. It is well structured and mostly economical, though the clip field list is slightly redundant with the clips parameter description.

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 two-parameter tool, the description covers both inputs and the expected output artifact clearly. Since an output schema exists, return-value details are not required here. The main missing context is explicit usage scenarios and error behavior, but an agent can construct a correct call from the provided information.

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%, but the description fully compensates by documenting both parameters: output_res_path is an absolute filesystem path for the output file, and clips is a list of dicts with name and path keys. Concrete examples for path values add useful meaning beyond the bare 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?

The description clearly states a specific action and resource: generate a master AnimationLibrary .tres file that references external animation clips. The purpose is unambiguous and distinct from the animation-related sibling tools, though it does not explicitly name or differentiate 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 intended use is implied by the description: create an animation library that stitches clips into a centralized .tres file. However, it does not explicitly state when to use this tool over alternatives, nor does it describe exclusions or prerequisites.

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 available, the description carries the full burden. It discloses both the core action and the return value. It does not describe failure behavior when no project is running, but the zero-parameter design limits ambiguity.

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?

A single sentence with no wasted words places the action and output first. Every part earns its place.

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 tool with no parameters and an output schema, the description fully covers the precondition ('currently running'), the behavior (stop), and the return value (final output). Nothing needed for correct invocation 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?

The input schema is empty, so there are no parameter semantics to clarify. The description correctly avoids inventing parameter guidance, matching the baseline for a zero-parameter tool.

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 uses a specific verb ('Stop'), a specific resource ('the currently running Godot project'), and adds a meaningful outcome ('return its final output'). This clearly differentiates it from sibling launch/run tools without requiring schema inspection.

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?

'Currently running' provides a clear usage condition: the tool only makes sense after a project has been started. It does not explicitly name alternatives like run_project, but the context is explicit enough to guide an agent.

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 provided, the description carries the full burden of behavioral disclosure. It states that it 'Edit[s] project.godot' but does not disclose whether this is destructive (overwrites existing settings), whether it requires write permissions, whether it is reversible, or what the impact is on the project beyond toggling the recorder. The mention of 'locking the render time-step' implies a side effect but does not explain consequences. This is a significant gap for a file-modifying 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?

The description is concise and front-loaded with the purpose, then lists parameters in a clear, readable format. The intro sentence could be slightly more direct ('Engine Activator' and 'perfect fps loop' are a bit verbose), but the structure is effective and each sentence adds value. It avoids redundant or extraneous 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?

The tool is simple with 4 parameters, but the description omits key contextual information: it does not explain what happens on success or failure, whether the project.godot file must already exist, or how the tool handles invalid paths. Although the context signals indicate an output schema exists, we don't have it, so the description should offer more about return behavior. The lack of usage prerequisites and error handling makes it incomplete for an agent that might need to know if a project is required.

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 description provides explicit explanations for all four parameters, which the input schema lacks entirely (0% schema coverage). It defines project_path as the absolute project directory, enable as the toggle, output_file as a res:// path with an example, and fps as the capture framerate with a default and a conditional note ('Only used when enable=True'). This fully compensates for the missing schema descriptions.

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 clearly states the verb ('Edit project.godot to toggle'), the specific resource (Godot's uncompressed video recorder), and the effect ('locking the render time-step to a perfect fps loop'). This distinguishes it from sibling tools like launch_editor or run_project, which focus on running or launching, not on editing project settings. The phrase 'Movie Maker Engine Activator' reinforces the specific function.

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 does not provide any guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., that the project must exist, that Godot must be installed), nor does it state when it would be inappropriate to use (e.g., if the project is already running). It simply explains the mechanism without context for decision-making.

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 provided, the description carries the full burden. It indicates a write operation ('resave') but does not disclose potential side effects, such as overwriting files, requirements (e.g., project not open), or reversibility. The lack of behavioral context is a significant gap for a mutation 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?

The description is two lines with no unnecessary words. The purpose is front-loaded, and the parameter explanation is concise. Every sentence earns its place.

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 mutation tool with no annotations, the description is incomplete. It omits usage guidance, side effects, and any note about return values (though an output schema exists). An agent would not know the risks or when to prefer this over other tools.

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% for the parameter, but the description provides meaningful semantics: it specifies 'project_path' as an absolute path to a Godot project directory. This goes beyond the schema's bare label 'Project Path', though it lacks format validation or preconditions.

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 clearly states a specific action ('Resave all resources') and its purpose ('regenerate UID files'), including a version constraint (Godot 4.4+). It is distinct from sibling tools like get_uid, which retrieves UIDs rather than regenerating 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 purpose implies when to use (when UID files need regeneration), but there is no explicit guidance on alternatives or when not to use. The description does not differentiate from other tools or provide context on typical scenarios.

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