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 states the action (run a command) but doesn't disclose side effects, whether the command may be destructive, require specific REAPER state, or return any output. For a tool that can execute arbitrary REAPER commands, 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, focused sentence that front-loads the action and resource. Every word earns its place, and it avoids unnecessary elaboration.

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 that executes arbitrary REAPER commands, the description is thin. It lacks information about return values, error handling, side effects, and prerequisites. The output schema is absent, and the description doesn't explain what happens after the command runs. An agent would need external knowledge to use this tool safely and effectively.

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 that command_id is a numeric command id, which adds meaning beyond the bare integer type. However, it doesn't provide details like valid ranges, how to find command IDs, or whether the command ID is a native REAPER ID or a custom one. The description adds some value but leaves gaps.

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 ('Run') and resource ('REAPER Main_OnCommand by numeric command id'), which clearly identifies the tool's function. It distinguishes itself from siblings like run_lua and reaper_call by specifying the exact REAPER API function and input type, though it doesn't explicitly name 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 description implies usage: use this tool when you need to invoke a REAPER command by its numeric ID. It doesn't explicitly state when not to use it or mention alternatives like run_lua for scripts, but the context of sibling tools and the specific API reference provide some 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?

The description is extremely transparent, detailing critical behaviors like the multiple syntax options for a single call object ({func, args} or {func, code}), the non-abortive error handling ('One failure does not abort the rest'), and its asynchronous nature ('Handles from earlier calls work later'). This is vital since annotations are absent.

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 packs a significant amount of technical detail into a compact paragraph. While slightly dense, every sentence adds value by defining the tool's core functionality and limitations.

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 there are no annotations or output schemas, this definition is highly complete. It addresses the 'how' (IPC hop), the 'what' (nested structure), and the 'under what conditions' (non-abortive failures), leaving no major gaps for the agent.

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 must explain the complex payload structure. It successfully details the available structures within the `calls` array items (e.g., 'Each call is {func, args} or {func, code} or {func, arguments}'), providing necessary meaning to the schema fields.

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 defines the tool's function as grouping 'Many operations in one IPC hop.' While clear, it doesn't explicitly name the category of operations (e.g., 'macro-execution' or 'bulk command execution') compared to its 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 usage is implied—use it when you need to run multiple related operations together for efficiency. However, it doesn't explicitly state *when* to choose this over a sequential series of calls to the listed 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?

With no annotations, the description carries the full behavioral burden. It does disclose important mutation semantics: set replaces all points and re-activates an inactive envelope. However, it omits other relevant behavior such as what list/get return, whether set requires the envelope to exist, and how track_index/envelope_index interact.

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 dense and front-loads the action modes, then moves into parameter-specific notes. It is appropriately sized, though the phrase 'value is the envelope's value' is tautological and the order of notes is somewhat ad hoc.

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 mutable 6-parameter tool with no annotations, no output schema, and no schema parameter descriptions, the description covers domain semantics well but leaves key gaps: track vs envelope indexing, list/get return behavior, and nested point fields. An agent could call set, but list/get usage remains under-specified.

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 explain all six parameters. It adds useful meaning for action, name, unit, value, and points, including gain/dB scaling, but never explains track_index (including the -1 minimum) or envelope_index, both of which are critical for locating the envelope.

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 identifies the resource as REAPER envelopes and names the three operations (list, get, set). 'Track envelopes' alone is slightly ambiguous as a verb, but the action enumeration makes the tool's purpose clear enough to distinguish it from siblings like item, fx, or send.

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 action modes and notes on unit=db and set behavior imply when each mode is appropriate, but there is no explicit guidance on choosing list vs get vs set, nor any statement of when to use this tool instead of sibling tools. Usage is inferable rather than spelled out.

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

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

With no annotations the description carries the full burden, and it does disclose useful behavior: track_index -1 addresses the master, set accepts normalized 0..1 or a display-formatted value resolved by text search, and set returns the formatted value actually applied. However, it says nothing about destructive semantics of delete, what preset does (save vs load vs recall), or whether bypass/move are idempotent or error-prone.

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?

Extremely dense telegram-style prose; every clause carries information, with the action enum front-loaded and the value-formatting rule following immediately. It reads tersely rather than bloated, though the run-on formatting of the set semantics could be split for readability.

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

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

For an eight-action, ten-parameter tool with no annotations and no output schema, the description covers the core mechanics but omits the parameter-to-action mapping, the meaning of the preset action, and any error behavior. An agent could probably invoke list or set correctly but would be guessing on move, preset, and bypass.

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% across ten parameters, and the description documents only the highest-value ones: action, track_index (-1 = master), value (REAPER normalized 0..1), and formatted (unit number or label like "3.2k"). Six parameters — param, preset, enabled, fx_name, fx_index, dest_index — are left entirely to name inference, which is a real gap even if most are guessable.

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?

Names the resource (track FX) and enumerates all eight actions in a compact action: list | add | params | set | delete | bypass | move | preset, so an agent immediately knows the surface area. Sibling tools are other domains (track, item, envelope), so the resource name does most of the differentiation work, but there is no explicit statement distinguishing when this belongs to track vs item FX.

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 action enum implies modes but there is no guidance on when to use this tool versus track, envelope, or run_lua, and no prerequisites (e.g. that an FX must be added before params/set/b bypass can target it). Nothing tells the agent which parameters are required for which action, leaving ten parameters to be inferred.

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 disclosure burden. It does valuable work by clarifying non-obvious units (fades in seconds, positions/lengths in beats) and the host-path requirement for import, but it says nothing about what update mutates, whether changes persist/are undoable, or what list 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?

Dense and front-loaded: the resource and action set come first, followed by unit clarifications and the import constraint. The telegraphic style wastes no words, though the sentence fragments make it slightly harder to parse than a fully formed brief.

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 13-parameter, multi-action tool with no annotations and no output schema, the description never says which parameters apply to which action (does list require track_index? does update require item_index?), leaving the agent to guess at the action/parameter matrix. It also omits any description of what list returns.

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 coverage across 13 parameters, the description explains the most confusing ones: fade_in/fade_out units, position/length in beats, path, and as_new_track. However, mute, loop, gain_db, track_index, item_index, and start_beats are undocumented, and the distinction between start_beats and position_beats is left ambiguous.

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 resource (media items on a track) and enumerates the three supported operations (list | update | import), so an agent can tell this apart from siblings like track, midi, or fx. It lacks an explicit 'this is not X' comparison, but the scope 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?

Usage is only implied through the action enum; there is no statement of when to choose item vs track or midi, nor prerequisites such as needing an existing track before importing. It does give one useful conditional hint (as_new_track=true makes new tracks) and a constraint for import (path must already exist on the REAPER host).

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 behavioral burden. It usefully discloses that times are absolute project beats, that 'replace' rewrites the whole take in one undo step, and that 'add' only appends. It still omits return format, failure behavior, and permission or track-index prerequisites.

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 resource and action list come first, followed by key behavioral distinctions. The telegraphic style packs a lot into a few lines without wasted sentences, though some phrasing is terse enough to be slightly cryptic.

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 13-parameter, seven-action tool with no annotations and no output schema, the description covers the most important action semantics and a few behavioral traits. It is not complete enough to guide correct use of many parameters or to explain return values, leaving meaningful 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%, so the description must compensate for all 13 parameters. It explains the 'action' enum values, gives partial meaning to 'ccs' (cc + value, program) and 'start_beats' (absolute project beats), and notes 'get' defaults for index/channel/muted. But it leaves 'pitch', 'velocity', 'length_beats', 'item_index', 'note_index', 'note_indices', and 'track_index' unexplained.

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 the resource ('MIDI on a track item') and enumerates all seven supported actions, so an agent can understand the tool's domain. It does not explicitly differentiate itself from siblings like item or track, but the MIDI-specific scope is clear enough.

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 provides useful guidance for choosing between 'replace' and 'add' (replace rewrites the whole take, add only appends), and explains how 'cc' inserts controller or program-change data. However, it gives no guidance on when to use this tool versus the sibling 'item' tool, nor any prerequisites or excluded scenarios.

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 does this well for save — creating missing folders, writing a copy with no dialog, an untitled project adopting the path, and the precondition that save-without-path needs a named project — but the other four actions receive no behavioral disclosure at all (no indication of whether they overwrite existing tempo/markers or how they fail).

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, front-loaded sentences with no filler; the action list appears before the save caveats. The telegraphic style ('save with path...') is dense but every clause carries operational 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?

For a multiplexed tool with five actions and eleven parameters, no annotations, and no output schema, the description covers only the save path. It leaves which parameters belong to which action and what each non-save action returns entirely to inference, which is inadequate for this complexity.

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

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

Schema description coverage is 0% across 11 parameters, and the description explains only the action enum and the role of path for save. It never maps bpm, numerator/denominator, start_beats/end_beats, position_beats, region_end_beats, is_region, or name to their actions, so the agent must guess the action-to-parameter association.

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 title-like sentence 'Project-level edits' is weak on its own, but the action enumeration (tempo, time_signature, time_selection, marker, save) precisely delimits what this tool touches, so an agent can tell it edits project-level attributes rather than items, tracks, or fx. It never names a sibling to differentiate against, 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?

Usage is implied through the action list rather than stated: an agent must infer that this is the tool for setting tempo, time signature, time selection, and markers. Conditional guidance exists only for save ('with path' vs 'without path'), and there is no statement of when to prefer a sibling such as transport or action instead.

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. While the description does explain pointer return format ({"__handle":"hN"}) and hints that handles can be passed back in, it omits key behavioral details: what happens if the function doesn't exist, whether calls are synchronous, whether they mutate project state, or error behavior. Since this can execute arbitrary ReaScript functions, the lack of safety/behavioral disclosure 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?

Highly concise: two sentences plus an example. The core purpose and pointer format are front-loaded, and the example is illustrative without extraneous content. 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 generic function-calling tool, the description gives the essential call pattern and pointer handling, but it lacks crucial operational context: no error handling, no mention of argument serialization rules, no discussion of side effects, and no differentiation from sibling tools like run_lua. With no annotations and no output schema, the description should do more to cover these 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%, so the description must compensate for the bare schema. It does explain func as a ReaScript function name and args as the argument list, with an example (CountTracks with arg 0). However, it doesn't clarify what argument types are supported, how args map to ReaScript parameters, or what the pointer handle string structure means beyond an example. It adds some meaning but leaves ambiguity for arbitrary functions.

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 (call any ReaScript function by name) and resource (ReaScript functions in REAPER). It also shows an example invocation with func and args. However, it doesn't explicitly differentiate from sibling tools like run_lua, which also executes scripts, leaving some ambiguity about when to use reaper_call over run_lua.

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 on when to use this tool vs alternatives such as run_lua or project tools. The sibling context includes run_lua, which could overlap significantly, and the description provides no criteria for choosing between them. It also doesn't mention constraints on function names, argument types, or error behavior.

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

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

With no annotations, the description carries the full burden and does so: it discloses that there is no undo, a long timeout, that media is set online (action 40101) first, and two refusal conditions with their cause (overwrite prompt hanging the bridge, soloed tracks). The return payload and warnings are also described, including measure=false skipping the loudness scan.

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 critical facts (no undo, long timeout) are front-loaded, and almost every clause carries operational information. The middle sentences are long and stacked with parentheticals, which slightly hurts scannability, but there is very little 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?

For a 14-parameter render tool with no output schema and no annotations, the description covers the mutation risk, failure modes, return shape and most parameters. The remaining gap is the four unexplained audio-format/range parameters, which an agent would have to guess at from the schema alone.

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

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

Schema coverage is 0%, so the description must compensate, and it explains roughly ten of the fourteen parameters: path (output folder), pattern (file name), bounds enum, stems + track_indices, media_online, allow_solo, solo_indices/mute_indices, and measure. channels, sample_rate, start_beats and end_beats are left entirely unexplained, which keeps it from a 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 opening 'Render.' is nearly tautological, but the following sentences make the operation concrete: rendering the master mix (or stems) to files in a folder. The distinction from siblings is implicit via 'stems=true' and 'track_indices', but no sibling tool is named, so it lands at a solid 4 rather than 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?

It states defaults ('Default: the master mix'), variants ('stems=true renders the selected tracks as stems'), and workarounds for the two documented refusals (allow_solo=true, media_online=false). It doesn't position itself against siblings like batch or action, so there is no explicit 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 carries the full burden and does well: it discloses that REAPER is frozen during execution, the timeout default (10) and ceiling (600), that errors carry the failing line, and a concrete io.popen background-and-poll workaround. It stops short of stating that arbitrary code runs with full host privileges and can mutate or destroy project state, which is the main omission for a code-execution 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?

Four tight sentences with no filler, and the most load-bearing facts (what it runs, how to return a value, when to prefer it) are front-loaded before the timeout and freezing caveats.

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

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

No output schema and no annotations, yet the description covers the return channel, error reporting shape, execution blocking behavior, timeout bounds, and an escape hatch for long operations. That is essentially everything an agent needs to invoke 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, and it largely does: it explains that `code` runs with `reaper` in scope and that `return` emits a value, and it spells out `timeout` semantics (seconds, default 10, max 600, intended for slow work). It doesn't say what return types serialize cleanly or name the `code` parameter explicitly, so it isn't exhaustive.

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

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

States a specific verb+resource ('Run a Lua snippet inside REAPER') and immediately scopes the environment ('reaper in scope') and result channel ('Use return to send a value'). The clause 'Best for multi-step work that would otherwise be many round-trips' distinguishes it from single-call siblings like reaper_call and action.

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

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

Gives a clear selection rule: use for multi-step work that would otherwise require many round-trips, implying single operations should use the narrower sibling tools. It also prescribes a pattern for slow work (launch in background and poll) and states the timeout's intended use. No explicit 'do not use for X' exclusion is given, which keeps it below a 5.

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

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

With no annotations, the description carries the full behavioral burden. It usefully discloses source/destination semantics and that the destination channel count is raised to fit routing, but it does not state that delete is destructive, permission/error behavior, or exactly what update changes.

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 the resource and action set, then follows with routing details. It is dense but efficient, with little wasted text, though it could be structured more clearly for scanning.

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

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

For a 10-parameter tool with no annotations and no output schema, the description omits `send_index` entirely and says nothing about list output or error behavior. It provides valuable routing context but leaves material gaps for safe 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?

At 0% schema description coverage, the description must compensate, and it does explain action, `track_index`/master, `dest_index`, volume_db, pan, mute, mode, and src/dst channel routing. However, `send_index` is never mentioned and ranges/defaults are left implicit, so the compensation is incomplete.

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 resource (track sends) and enumerates the supported actions, so an agent can tell it manages send routing rather than tracks, items, or FX. It does not explicitly contrast itself with sibling tools, which keeps it from a 5.

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

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

The action enum supplies operation-level guidance and `track_index` is clarified with `-1 master`, but there is no explicit when-to-use vs alternatives or prerequisites for add/delete/update. Usage is implied by action names rather than actively guided.

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 behavioral burden. It discloses returned fields, clarifies that dirty means unsaved changes, and explains that detail=true adds arrangement facts, but it does not explicitly state read-only behavior, side effects, or error handling for a broken bridge.

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 and dense: it states the core status check first, then usage guidance, then parameter behavior. Every sentence contributes useful information without unnecessary padding.

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

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

With no annotations and no output schema, the description must explain enough about returned data, and it does list the key status fields and the extra detail fields. It could be more complete by specifying the default detail behavior or failure mode for an unavailable bridge, but it is sufficient 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% for the single optional detail parameter, so the description must compensate. It does so by explaining that detail=true adds time signature, length in beats, markers, and per-track MIDI/audio facts, though it omits the default when detail is omitted.

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, checking the Lua bridge, and enumerates exactly what state is returned: tempo, play state, tracks, any_solo, master_mute, and dirty. This makes its role distinct from sibling tools such as project, transport, and render.

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

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

It gives clear usage context with 'Call first' and the prerequisite 'clear a lingering solo before rendering.' It does not name alternative tools or explain when not to use this one, but the operational guidance is specific.

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 full behavioral burden. It valuably discloses that bus disables the source tracks' direct send to the master/parent, but it does not warn that delete is destructive, describe return behavior, or state permissions/constraints.

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 three compact sentences, front-loads the purpose and action list, then adds only the non-obvious update and bus details. 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?

This is a complex multi-action tool with eight parameters, no annotations, and no output schema. The description adequately covers update and the tricky bus action, but leaves list, add, delete, and index semantics under-specified.

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 meaningful semantics for update fields, pan's -1..1 range, and bus's source_indices routing, but leaves 'index' unexplained and does not clarify parameter usage for add, delete, or list.

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 resource ('Track operations') and enumerates the five supported actions, so an agent can tell what the tool does. It does not differentiate the tool from siblings such as item, send, or fx, which is the main remaining gap.

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 lists actions but gives no explicit guidance on when to use this tool versus alternatives like send or fx, and no when-not conditions. The bus explanation is behavioral detail, not usage 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It names actions but does not describe their effects (e.g., whether 'record' starts or toggles recording, what 'goto_start' does to playback state, or side effects like project state changes).

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 exceptionally brief and front-loads the purpose, with no fluff or redundant prose. The action list is redundant with the schema but arranged 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?

For a simple one-parameter control tool, the description still leaves critical gaps: no explanation of action semantics, no output/return expectations, and no preconditions (e.g., whether a project must be open). An agent cannot reliably decide which action to invoke without more 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%, so the description must compensate. It merely repeats the enum values from the schema without adding meaning—'toggle_repeat' and 'goto_start' are left to the agent's inference, and the description does not explain the purpose or expected behavior of each action.

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 'Playback control' and lists six transport actions, giving a general sense of purpose. However, it is vague about the resource (e.g., DAW transport, project) and does not differentiate from siblings like 'action' or 'status'.

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 the listed siblings. There is no mention of alternatives, preconditions, or scenarios where a different tool would be more appropriate.

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