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

No annotations are present, so the description carries the full burden of behavioral disclosure. It only names the action and target; it does not reveal whether delivery is asynchronous or synchronous, how failures are handled, whether the message is copied per actor, or what side effects occur. This is a significant gap for a side-effecting 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 a single, front-loaded sentence with no filler. Every word contributes to identifying the operation and its scope, which is ideal for a tool of this simplicity.

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 tool with no annotations and no output schema, the description leaves important decisions to the agent: when to use broadcast versus targeted send, what message semantics are expected, and what the runtime behavior will be. The agent can infer the basic call shape but not the operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, and the description adds no meaning beyond calling it 'a message'. It does not explain the required 'type' field, how 'payload' is used, or what message values are valid. With only one parameter, the description should compensate more for the schema's lack of detail.

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 ('Broadcast'), the resource ('a message'), and the exact scope ('all registered actors in the current ActorSystem'). It is clear and implicitly contrasts with the sibling 'actor_send_message', which likely targets a single actor, though it does not explicitly name that 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?

The phrase 'all registered actors' implies the fan-out use case, and the sibling actor_send_message suggests a single-target alternative, but the description does not explicitly say when to choose this over targeted messaging or describe any prerequisites. Usage guidance is mostly 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?

With no annotations, the description must disclose behavioral traits. It states it returns a count but does not mention that it is a read-only operation, does not destroy or modify the inbox, or whether it has side effects. For a query tool, this is a minimal expectation. The description is too brief to disclose non-obvious behavior.

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, clear sentence with no verbosity issues. It is acceptably concise and front-loaded with the main action. However, it could use an additional sentence for usage guidance without becoming too long, so it earns a 4.

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 a simple interface (one parameter, no output schema), but the description omits critical context: what the return value looks like (e.g., integer vs. formatted string), whether the inbox is cleared after reading, or any side effects like error conditions for invalid actorId. With no annotations or output schema, the description is insufficient for an agent to use the tool safely and correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% coverage, meaning the description must compensate for the undocumented 'actorId' parameter. The description mentions 'an actor's inbox' which implies actorId identifies the actor, but it does not clarify the format or identifier type (e.g., numeric ID, string name). Baseline is 3 because the description provides some context beyond the schema, but not enough to fully clarify the parameter.

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 that the tool returns the count of pending messages in an actor's inbox. It uses a specific verb ('Return') and resource ('number of pending messages in an actor's inbox'), which is distinct from siblings like actor_send_message and actor_broadcast that send messages.

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 explicitly state when to use this tool versus alternatives, nor does it mention any prerequisites (e.g., 'Use this to check if an actor has pending messages before processing'). It only implies usage by saying 'Return the count'.

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 to rely on, the description carries the transparency burden. It discloses two behavioral traits: the message is queued rather than synchronously handled, and processing occurs on the next flush pass. It stops short of describing error behavior or whether the message is delivered at most once, but the core side effect is clear.

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, front-loaded with the action, with no filler or repeated schema information. Every word contributes meaning.

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 sufficient for a low-complexity side-effect tool: it states the action, target, and asynchronous processing behavior. There is no output schema to document, though a note on failure handling or message ordering would make it 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 parameter coverage is 0%, so the description must explain the parameters beyond their names. 'actorId' is loosely implied by 'specific actor' and 'message' by the verb 'enqueue', but the description adds no semantics about required message type, payload constraints, or behavior when the actor doesn't exist.

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 ('Enqueue') and clearly identifies the resource ('a specific actor's inbox'), making the operation's intent unambiguous. The phrase 'specific actor' also implicitly differentiates it from broadcast-style messaging among the sibling tools.

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 states that the message is enqueued and later processed on the next flush pass, which gives useful context for when this tool is appropriate. However, it does not directly contrast with actor_broadcast or other sibling tools, so the agent must infer the distinguishing conditions.

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. 'Return reference documentation' clearly indicates a read-only information-retrieval operation with no side effects weeds, and the function list further sets expectations about the content. It does not describe the format or size of the returned documentation, but the behavior itself is clear.

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, front-loaded sentence states the verb ('Return'), the object ('reference documentation'), and the exact scope (EmptySock LayerSystem APIs). No redundant text 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?

For a zero-parameter, read-only documentation tool, the description tells an agent what it will get and which APIs are covered. It stops short of describing the result layout or how the reference material is presented, but nothing critical is missing for selecting and invoking such a simple 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 tool takes zero parameters)Skip, so the schema already fully describes the input surface (none). The description adds no parameter-specific meaning, but none is needed. The baseline for zero-parameter tools 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 action ('Return reference documentation') and a precise subject (EmptySock LayerSystem API) with the exact list of covered functions (setVisible, setParallax, etc.). It is immediately distinguishable from all sibling tools, which perform scene/save/physics operations rather than returning API reference material.

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 implicitly tells an agent when this tool is useful — when EmptySock layer API reference documentation is needed — and the sibling context makes alternatives obvious. However, there is no explicit guidance about when to prefer this tool over, say, gms2_inspect_project or other documentation-capable siblings, and no exclusions are stated.

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 disclosure; it explicitly states 'Read-only — does not modify any files,' which is the key trait an agent needs before invocation. It also discloses the JSON summary format of the return value. Missing finer error-case behavior (e.g., malformed or missing project files), but for a simple read tool the core behavioral profile is covered.

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. The opening verb is front-loaded, the return contract is stated in one clause, and the safety disclosure is appended concisely. 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 single-parameter, annotation-free, output-schema-free tool, the description covers the operation, the result shape, and the read-only guarantee. The only notable gap is error handling behavior for missing or invalid .yyp files, which is a minor omission for such a low-complexity 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% for the single yypPath parameter, so the schema already documents path semantics; the description restates 'project file' without adding new detail about allowed path forms or constraints. Baseline 3 applies because coverage is high and the description does not meaningfully extend parameter meaning.

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 verb (Read), a specific resource (GameMaker Studio 2 .yyp project file), and enumerates the return payload (project name, asset counts by type, object/script names). No sibling tool targets GameMaker project inspection, so it is cleanly distinguished from the navmesh/physics/scene/save/actor 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?

Usage is implied clearly: the agent should call this when it needs an overview of a GameMaker project file. However, the description never explicitly says when to use it versus alternatives or when not to use it, so there is no direct guidance beyond the purpose statement.

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 the return behavior (ordered waypoints or empty array) and the algorithm (A*). However, it does not mention what happens if the navmesh is not loaded, if points are out of bounds, or any error conditions. For a read-only query tool, it is moderately transparent but has 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?

A single, well-structured sentence that front-loads the core action and result. No wasted words; every phrase adds meaning (A*, loaded navmesh, return type).

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 straightforward pathfinding tool with three simple parameters and no output schema, the description covers the essential aspects: what it does, the input type, and the return format. It does not detail error handling or edge cases, but these are not critical for basic usage. The description is sufficient for an agent to invoke it correctly 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?

Schema description coverage is only 33% (only mapId has a description). The description adds the phrase '2D points' clarifying that from/to are coordinates, but it does not explain coordinate systems, units, or edge cases. It provides marginal value beyond the schema, but not enough to fully compensate for the low 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 clearly states the verb ('Find'), the resource ('A* path on a loaded navmesh'), and the output ('ordered array of waypoints or empty array'). It distinguishes from physics raycasts and scene tools, and implicitly from navmesh_nearest_node by focusing on path finding between two points.

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 mentions the prerequisite 'loaded navmesh', which implies the navmesh must be loaded first, but it does not explicitly state when to use this tool versus alternatives like navmesh_nearest_node. It offers context but no exclusions or alternative 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?

With no annotations, the description itself carries the full burden. It reveals that the returned node is 'walkable' and uses a 'world point', which is useful, but it omits key behavioral details: what happens if no node is walkable, whether the point is clamped/projected, return structure, or whether the map must be loaded.

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 sentence with no wasted words. The primary action and resource are front-loaded, and every word contributes meaning.

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 appears conceptually simple, but with no annotations and no output schema, the description should clarify expected inputs and outputs. It does not describe the return value, error conditions, or coordinate-system behavior. For an agent to call it correctly, too much 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 0%, so the description must clarify the parameters. It clarifies that 'point' is a world point, which helps, but 'mapId' is left undocumented and the coordinate units/space of x/y are not fully specified. The nested object format is not explained in the description.

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 ('Return') and resource ('nearest walkable node on the navmesh') given a world point. It is clear, but it does not explicitly differentiate from the sibling navmesh_find_path, though the noun 'node' versus 'path' implies the 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 gives no guidance on when to use this tool versus navmesh_find_path or other physics/scene tools. There is no stated when-not-to-use, prerequisite like an active map or loaded navmesh, or comparison to 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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It does disclose the dual read/write behavior and the exact trigger for writing, which is useful. However, it does not describe the return value, whether writing merges or replaces the existing configuration, or how errors like unknown emitter IDs are handled.

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 just two sentences with no filler, and the core purpose ('Get or set') is front-loaded. Every clause contributes essential guidance about how to invoke 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?

The description covers mode selection and resource identification, which is enough for a basic invocation. But with no output schema and no annotations, it omits important contextual details like what a read returns, what a write returns, and whether the write is a partial update or a full replacement, leaving some ambiguity about side effects.

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 adds the key semantic that `config` is optional and controls read vs write mode, and the schema property names are largely self-explanatory (emitRate, maxParticles, etc.). Still, it leaves unspecified details like emitterId format, value ranges, units, and whether omitted config fields are preserved or reset on write.

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 specific verbs ('get' or 'set') and a precise resource ('ParticleSystem emitter configuration' keyed by emitter ID). It clearly distinguishes both modes and is distinct from the sibling tools, which target other systems like physics, scenes, or save data.

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 explicitly states when to read vs write: omit `config` to read, provide `config` to write. No overlapping sibling tool is mentioned, but the conditional instruction is clear enough for an agent to select the correct behavior without further context.

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 behavioral disclosure. It clearly indicates a read-style operation by saying 'Return', and it names the returned fields, but it does not mention failure behavior, coordinate units, or whether the entity must already have a physics body. This is adequate but incomplete.

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, well-structured sentence with no filler. It front-loads the action and output, then states the input scope concisely.

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 one-parameter getter with no output schema, the description covers the essential input and output. It lacks details about error cases, units, or coordinate systems, but the tool's complexity is low and the description is largely sufficient for an agent 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 0%, so the description must compensate. It only repeats the parameter name ('entityId') through the phrase 'by entity ID' and adds no detail about what IDs are valid, what entity types are expected, or how missing or invalid IDs are handled. The sole parameter is self-explanatory, but the description adds little semantic value.

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 clear resource ('physics body'), and names the exact data returned: position, velocity, and angular velocity. It is sufficiently distinct from sibling tools like physics_raycast_2d/3d and navmesh tools, which serve different purposes.

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 choose this tool over alternatives, nor any mention of prerequisites or exclusions. The phrase 'by entity ID' implies an input requirement, but the description does not explain when this tool should be used versus scene_entity_info or other physics 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?

The description makes the read-only selection behavior clear and notes the 2D collider scope. However, with no annotations, it omits details like whether touching colliders count, coordinate-space assumptions, or any side effects (likely none).

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?

One tightly worded, front-loaded sentence. No filler or restatement of the tool name; every word adds meaning.

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?

While the core behavior is clear, the description omits important context for correct use: layerMask semantics, coordinate space, whether touching colliders count, and what happens when nothing overlaps. With no annotations or output schema, an agent has limited guidance beyond the basic query shape.

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 descriptions are 0%, so the description must carry semantic weight. It conveys that center/radius define the circle, but gives no meaning or usage guidance for the optional layerMask parameter and does not explain units or how center coordinates are interpreted.

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 ('Return'), a specific geometric query ('2D colliders overlap a circle'), and the output ('entity IDs'). It is immediately distinguishable from sibling raycast/pathfinding tools.

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 on when to choose this tool over alternatives like physics_raycast_2d, navmesh_find_path, or scene queries. It neither lists use cases nor exclusions, so the agent gets no routing help.

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 behavioral burden. It clearly discloses the core outcome: cast a ray and return the first hit entity, hit point, and normal. However, it does not disclose behavior on no-hit cases, whether the ray interacts with all physics objects by default, or any coordinate-space assumptions, so transparency is partial.

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 concise, front-loaded sentence with no wasted words. It states the action and the key returned values immediately. It loses one point because its brevity causes it to skip important parameter and edge-case 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?

Given four parameters, no annotations, no output schema, and 0% schema description coverage, this description is not complete enough. It names the key return values but leaves out no-hit behavior, layer mask semantics, maxDistance interpretation, and whether the raycast is read-only, which an agent needs to call the tool confidently.

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 adds no meaning for any of the four parameters. It does not mention origin, direction, maxDistance, or layerMask, leaving the agent to rely entirely on the bare schema with no explanation of semantics, normalization, units, or how the layer mask affects results.

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 verb and resource: cast a ray in 2D physics space and return the first hit entity, point, and normal. The '2D' qualifier clearly distinguishes this from the sibling physics_raycast_3d, so an agent can separate it by name and description.

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 inferred from '2D physics space', which suggests when to use it versus physics_raycast_3d or navmesh tools, but there is no explicit statement about when to prefer this tool or when not to use it. The usage guidance is implied rather than stated.

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 disclose behavioral traits. It states the return is 'the first hit,' implying the closest intersection, but does not mention behavior on a miss (e.g., null result), whether the layer mask filters hits, or if the ray is infinitely thin. It lacks essential behavioral context for an agent to know what to expect.

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, short sentence with no filler. It front-loads the verb and direct object, making it immediately clear. Perfectly concise and efficiently structured.

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 4 parameters, nested objects, no output schema, and no annotations, the description is severely incomplete. It does not explain the return value structure, error handling, coordinate system, or any usage nuances. An agent would not know how to interpret the result or handle edge cases, making the tool impractical to use reliably.

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 for parameter meaning. It does not mention any parameter, such as the format of origin/direction vectors, the meaning of maxDistance (units), or how layerMask is interpreted. The parameter names are self-explanatory but the description adds no semantics beyond them.

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: 'Cast a ray in 3D physics space (Rapier3D) and return the first hit.' It clearly differentiates from sibling tools like physics_raycast_2d by specifying 3D and the physics engine. The purpose is unambiguous and distinct.

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 provided on when to use this tool versus alternatives such as physics_raycast_2d or physics_overlap_circle. There are no explicit when-to-use, when-not-to-use, or alternative suggestions. The agent must infer usage from the name and description alone.

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 behavioral burden. It does disclose that the operation removes a save slot from persistent storage, which is useful for a destructive call, but it does not mention whether deletion is reversible, what happens when the slot does not exist, or what is returned.

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

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

At seven words, every word contributes and the core action is front-loaded. There is no filler or repetition.

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 tool with no annotations and no output schema, this one-liner is incomplete: it leaves the agent guessing about slot format, success/error signaling, and failure behavior. It is enough to understand the intent but not enough to invoke the tool with confidence in all cases.

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 only gives 'slot' as a string with no description, and schema description coverage is 0%. The description's mention of 'a save slot' weakly links the parameter to the resource, but it does not explain expected slot format, valid values, or how the slot is selected.

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 the operation explicitly: 'Delete' is a specific verb, 'save slot' is the resource, and 'from disk' adds location. This clearly differentiates it from sibling tools like save_read, save_write, and save_list, which perform non-deletion operations.

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 guidance or alternatives are provided; the only signal is the verb 'Delete', so usage must be inferred from intent. There are no conditions, prerequisites, or exclusions stated.

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?

There are no annotations, so the description carries the behavioral disclosure burden. 'List' clearly implies a read-only enumeration and no destructive side effects, but the description does not state what the returned items look like, whether subdir changes the scope, or how this relates to other save operations. This is adequate but minimal.

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 front-loaded sentence with no filler. Every word—'List', 'all', 'available', 'save slots'—contributes to understanding the tool's core behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (one optional parameter, no output schema), the description conveys the high-level purpose well. However, it leaves the return value's structure unspecified and does not mention that subdir can restrict the listing, though that detail is present in the schema. This is a minor gap rather than a blocking one.

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 'subdir' already documented as 'Optional sub-directory within save base (no traversal)'. The description adds no parameter-specific meaning, so the baseline score of 3 applies because the schema handles parameter documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and a specific resource ('save slots'), making the tool's purpose immediately clear. It also distinguishes this tool from sibling save operations like save_read, save_write, and save_delete by framing it as an enumeration rather than an operation on a single save.

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 about when to choose this tool over save_read, save_write, or save_delete. There is no mention of typical workflows such as scanning available slots before reading or writing, nor any explicit exclusions.

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. It does disclose that it reads from disk and returns JSON data, which implies a non-mutating operation. However, it does not mention error behavior for missing slots, whether the JSON is parsed or raw, or any side effects beyond reading.

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 concise sentence, front-loads the verb and object, and includes the key output type (JSON data). No filler or redundancy.

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 read tool with one documented parameterchers, the description covers the core behavior and output. It lacks notes on failure modes, whether the slot must already exist, or how the returned JSON is structured, which leaves some ambiguity for an agent calling this 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 input schema already fully documents the slot parameter with an example, and the description references 'a save slot' without adding meaningful details beyond the schema. No additional parameter semantics are contributed.

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 ('Read') and resource ('a save slot from disk') and states the return value ('its JSON data'). This clearly distinguishes it from the sibling tools save_write, save_delete, and save_list.

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, nor any conditions or prerequisites. The description states what it does but does not explicitly frame it as the read counterpart to save_write/save_delete or mention when it is appropriate or inappropriate.

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 for behavioral disclosure. It states the side effect of writing data to disk, but does not disclose whether the operation overwrites an existing save or creates a new one, whether it is atomic, or what failure modes exist (e.g., disk full, invalid slot). The description is minimally transparent about the outcome but lacks depth on error behavior and data durability.

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 concise sentence that is front-loaded with the primary action and subject. It contains no wasted words and is efficient, though it could benefit from an additional sentence about slot semantics, but the brevity is not excessive.

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 write operation with no annotations and no output schema, the description is minimalistic. It does not state whether the operation overwrites existing data, whether it creates a new save slot, or what the return value (if any) is. Given the tool's simplicity (2 parameters), the description is adequate for basic invocation but lacks details on overwrite behavior and return type, leaving some ambiguity.

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 'data' parameter is described as 'Arbitrary save data', which adds a small layer of meaning, but the 'slot' parameter has no description in the schema, and the description does not clarify its format or constraints. However, since schema coverage is 50%, the description partially compensates by specifying the data type (JSON) and purpose (save slot), but it does not clarify slot semantics (e.g., numeric index vs string key). This is a moderate addition over 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 clear verb ('Write') and resource ('JSON data to a save slot on disk'), making its purpose unambiguous. The wording clearly identifies it as a save-write operation distinct from siblings like save_read, save_delete, and save_list.

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 is implied to be the mechanism for writing JSON data to a save slot, but it does not explicitly state when to use it versus alternatives like save_update or save_overwrite if they existed. It does not mention prerequisites such as 'slot' format ('e.g., slot number or key') or whether the slot must exist. The context clarifies it is for writing, but the usage context is sparse.

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 that the tool mutates a scene and returns the new entity's ID, but it does not state whether the operation is reversible, whether components must already exist, or what happens if the sceneId is invalid. For a mutation tool with zero annotation coverage, this is a significant 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 a single efficient sentence that front-loads the action and return value. It earns its place, though it could add a bit more context without becoming bloated.

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, no output schema, and 0% parameter coverage, the description is too thin. It does not explain the 'components' parameter, any constraints on 'tag', or error behavior. An agent would need to guess or inspect other tools to call this 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 0%, so the description must compensate. It only explains the return value, not the meaning of 'tag' or 'components'. The description adds no semantic detail beyond the schema's bare property names, leaving the agent to guess what values are valid.

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 ('Add') and resource ('a new entity to a scene'), and mentions the return value (entity ID). It is clear enough to distinguish from sibling tools like scene_list_entities or scene_entity_info, though it does not explicitly name them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., scene must exist), nor does it contrast with scene_entity_info or scene_list_entities. Usage context is only implied by the verb 'Add'.

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 burden. The phrase 'Return...' implies a read-only operation, and the outputs are enumerated (tag, active state, component list). However, there is no disclosure of edge cases, failure behavior, or whether this reflects live state vs cached state. With no annotations, more behavioral context would be expected, but the tool's scope is at least made clear.

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?

Single clear sentence; no filler. Front-loaded with what it returns.

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 read-only info tool with no annotations, no output schema, and no parameter descriptions, an agent needs more context: what the component list looks like, whether tag/state can be absent, ownership/visibility rules, and error behavior. The description is minimal but accurate.

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% – neither parameter is explained in the input schema. The description implicitly ties the parameters to a scene and an entity ('specific entity', presumably within a scene), which helps, but it doesn't tell the agent how sceneId/entityId should be formatted, whether entityId is local to the scene, or what values are valid. Since coverage is 0%, the description needed to do more than infer the obvious parameter 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 names the exact resource (a specific entity) and the specific data returned: tag, active state, and component list. It clearly distinguishes the tool from raw entity listing (scene_list_entities) or component access (scene_get_component), though it doesn't explicitly name sibling alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus scene_get_component or scene_list_entities. The description says what it returns, but not the context where this is the right choice, nor exclusions/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 behavioral burden. 'Retrieve' implies a read-only operation and 'serialised state' hints at the return format, but the description does not disclose error behavior, missing entity/component handling, or the exact serialization format.

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 sentence with no filler words. The core verb, resource, and scope are front-loaded, and every word 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 simple three-parameter getter, the description plus the componentType schema note is minimally viable, but the lack of an output schema makes the 'serialised state' return type vague, and the two identifier parameters remain underspecified. It is usable but leaves important retrieval details implicit.

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 low at 33%, with only componentType described, and the description does not compensate for the undocumented sceneId and entityId parameters. It gives no guidance on where these identifiers come from or how they should be formatted.

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 ('Retrieve') and a specific resource ('serialised state of a specific component on an entity'), making the tool's purpose clear and distinguishing it from entity-level siblings such as scene_entity_info. It does not explicitly name an alternative it is not, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use or when-not-to-use guidance is provided; the description only states what the tool does. An agent is not told how to choose this over scene_entity_info or scene_list_entities, nor are any prerequisites or context given.

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 present, the description carries the full burden. The phrase 'currently active' provides a useful time-scoped, read-only flavor, but the description is silent on output ordering, whether destroyed/hidden entities are excluded, or what an empty scene 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?

Seven words with zero filler. The term 'currently active' is meaningful and carries the behavioral nuance, and the sentence is front-loaded with the verb and resource.

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?

Adequate for a simple one-parameter list tool, but with no output schema and no annotations, it does not state the return format (e.g., plain array of strings), ordering, or behavior for empty or invalid scenes.

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 sceneId parameter has no documentation. The description only ties 'in a scene' loosely to the parameter, adding no real meaning beyond what the parameter name itself conveys (format, valid values, existence requirements).

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 ('List') and resource ('all entity IDs'), and scopes it to the active set in a scene. The word 'IDs' distinguishes this from sibling scene_entity_info, though it never names that alternative 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?

The use case is implied: call this when you need to enumerate the current ids in a scene. However, there is no explicit when-to-use/when-not-to-use guidance or mention of how it relates to sibling tools such as scene_entity_info or scene_create_entity.

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 does disclose the output shape (JSON object containing nodes and edges), which is useful behavioral context, but it does not explicitly state whether the export is read-only, handle missing scenes, or affect state. A stronger description would add a one-line guarantee of non-mutation.

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 that front-loads the verb, resource, and expected output with no filler or repetition of the schema. 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 simple 2-parameter export tool this is mostly complete: the agent knows what to call and what to get back. However it lacks any mention of the behavior of the optional graphId, any error or fallback behavior, and there is no output schema to give the agent more shape on the JSON structure. It covers the essentials but leaves some contextual 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?

The schema covers only graphId with a description; sceneId has none, giving 50% coverage. The description adds only a vague 'named scene' gloss for sceneId and says nothing about how graphId influences the export. Given the incomplete schema coverage, the description does not sufficiently compensate for the missing parameter context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Export') with a specific resource (the Story Graph for a named scene) and tells what the result contains (JSON with nodes and edges). No sibling tool targets the story graph, so it is clearly distinguishable from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The word 'Export' implies that this is the tool to call when story-graph data is needed, but there is no explicit 'when to use' statement, no exclusions, and no context about when other sibling tools would be more appropriate. The guidance is acceptable but only implied.

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