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

With no annotations provided, the description carries the full burden. It details note format, layer_type values, swing_offset behavior (applied to odd-index notes), and that chiptune_program is ignored for drums. Missing details on side effects or permissions, but adequate for core 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 paragraph with clear structure: purpose, stacking instruction, then parameter details. It is informative without being overly verbose, though could be slightly tighter.

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 7 parameters (4 required), nested arrays, no annotations, and an output schema, the description covers the key aspects. It explains independent layers, note formatting, swing, and chiptune programs. It omits error conditions and limits, but is sufficient for typical use.

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 compensates well. It explains the notes array format, accepted layer_type values, swing_offset usage, and chiptune_program options. It does not describe midi_channel, but other parameters are well covered.

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 'Add ONE independent layer/channel to the project', specifying a concrete action and resource. It gives examples of layer types (melody, harmony, bass, drums) and explains stacking via multiple calls, distinguishing it from siblings like list_layers.

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 that the tool can be called multiple times to stack layers, each with its own length and rhythm. It does not explicitly state when not to use it or compare to alternatives, but the context is clear.

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

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

No annotations provided, so description carries the burden. It discloses default destination directory and that MIDI does not natively store loop metadata, implying the return value is important. However, it does not mention whether it overwrites existing files or required permissions.

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

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

Three short sentences with no redundancy. First sentence states purpose, second gives ordering, third explains default directory. Every sentence adds value.

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 that output schema exists (not shown), description mentions return value (loop metadata). Covers key aspects: what it does, order, default path, and engine context. Could add overwrite behavior but not essential.

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 description must compensate. It only adds meaning to destination_dir ('Default destination_dir is assets/midi/ (or NOBU_MIDI_DIR)') but provides no information about project_name beyond its presence in 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?

Description explicitly states verb 'Render all project layers into a single multi-track .mid file', clearly identifying the resource and output format. Distinguishes from siblings like add_layer which add layers rather than export.

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

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

Explicitly says 'Call last, after all add_layer calls', providing sequential guidance. Mentions use of returned loop metadata for configuring engines, but does not state when not to use or alternative 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 full burden. It states it generates correct MIDI notes but does not specify the format, range, or details about the output. The output schema exists but the description lacks behavioral context like return structure.

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

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

Four sentences, front-loaded with purpose. Efficient, though could slightly tighten phrasing without losing clarity.

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 three parameters, output schema exists, and low complexity, the description covers purpose, usage, and parameter semantics adequately. It is sufficient for agent 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 coverage is 0%, but the description explains acceptable values for scale_type (listing all options) and implies octaves defaults to 2. It adds meaning beyond the schema's type definitions, though octaves could be explained more explicitly.

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 tool generates MIDI notes for a musical scale, acting as a palette of valid pitches. It distinguishes from the sibling 'suggest_scale_for_mood' by specifying its 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?

Explicitly instructs to use this tool (or suggest_scale_for_mood) ALWAYS before manually inventing note numbers to avoid out-of-key melodies, and names the alternative 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. It discloses that it lists layers with note counts and duration, implying a read operation with no side effects. This is sufficient for a simple list 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 sentences. The first sentence states the action and output, the second provides usage guidance. No wasted words; information is front-loaded.

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

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

Given an output schema exists and sibling tools are listed, the description covers the tool's primary purpose and usage context. It lacks details on error handling or prerequisites, but is sufficient for a straightforward tool.

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

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

There is one parameter (project_name) with 0% schema coverage. The parameter is self-explanatory and the description adds context by linking it to 'the project'. Given only one obvious parameter, this is adequate.

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 'list all layers already added to the project, with note counts and duration for each,' providing a specific verb and resource with attributes. It distinguishes itself from siblings like add_layer and export_midi.

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 explicitly recommends using this tool before export_midi to verify all planned layers were added and to decide whether to add more. It gives clear context but does not state when not to use it.

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

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

No annotations are provided, so the description carries the full burden. It describes the action as scheduling a tempo change but does not disclose behavioral traits such as whether multiple tempo changes can coexist, if the change is reversible, or if it has any destructive side effects.

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 with no wasted words. The first sentence defines the core function, and the second provides concrete, memorable examples. Perfectly concise.

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 an output schema, the description need not explain return values. However, the description lacks detail on parameter semantics and behavioral traits, making it not fully complete for a tool with no annotations and zero schema documentation coverage.

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. While it mentions 'at a specific absolute beat' (time_in_beats) and 'tempo change' (new_bpm), it does not explain the project_name parameter, and the descriptions are minimal. More detail is needed to fully clarify 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?

Clearly states the tool schedules a tempo (BPM) change at a specific absolute beat. The verb 'Schedule' and resource 'tempo change' are specific, and the examples distinguish it from sibling tools that deal with layers, scales, or project management.

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?

Provides clear use cases like 'speed up when entering boss phase 2' and 'slow down for tension before a climax', indicating appropriate contexts. However, it does not explicitly mention when not to use or offer alternative 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?

Describes the empty project state, layer independence, and hardware analogy beyond a simple create. No annotations provided, but lacks mention of potential errors or idempotency.

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 informative, starting with an imperative instruction. However, it could be slightly more streamlined without losing the layering concept explanation.

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 simplicity and the presence of an output schema, the description covers the main purpose and usage well. It lacks constraints on parameter values (e.g., BPM range) but is otherwise 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?

With 0% schema description coverage, the description should explain the parameters 'project_name' and 'bpm', but only mentions them in the context of the tool name. No additional semantic information is added.

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 ('Creates an empty project') and resource, and distinguishes from siblings by positioning as the first step and referencing 'add_layer' as subsequent 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?

Explicitly instructs 'ALWAYS call this tool first, before any other' and explains the context of independent layers, providing strong when-to-use guidance.

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 explains the mapping from mood to scale and the return value (scale and MIDI pitches). However, it does not explicitly state whether the tool is read-only, whether it has side effects, or any error conditions. The description assumes a non-destructive planning step but lacks explicit behavioral disclosure.

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 well-structured: first sentence states when to use, then mapping and accepted moods, then return value. Every sentence adds value without redundancy. It is front-loaded with the most critical usage instruction.

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

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

With an output schema present, the description still adds value by explaining the return value and providing a detailed mood-to-scale mapping. It covers all essential aspects for correct invocation: when, what inputs (mood, tonic), and expected output. Lacks only minor details like error handling or edge cases, but is sufficient for most contexts.

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 lists accepted moods (explaining mood), implies tonic_midi is the root note, and mentions octaves indirectly by saying 'returns list of MIDI pitches ready for add_layer,' but does not explicitly describe the 'octaves' parameter or its default behavior. Partial compensation but not thorough.

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 tool maps emotions/moods to musical scales and lists specific moods and scale mappings. It distinguishes itself from siblings like 'generate_scale' by explicitly saying to use it 'BEFORE composing any melody, harmony, or bass line' and noting it returns MIDI pitches ready for 'add_layer', making its purpose unique.

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 explicitly states when to use the tool ('BEFORE composing any melody, harmony, or bass line') and provides the accepted moods. However, it does not explicitly contrast with siblings like 'generate_scale' or mention when not to use it, slightly reducing clarity on alternatives.

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