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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's 'risk-gated' adds minimal new context. It does not disclose what operations are destructive, whether approvals are required (despite approvalId in schema), or what side effects may occur. The description adds a vague behavioral hint but fails to provide meaningful transparency beyond annotations.

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, but brevity without substance is under-specification, not conciseness. It fails to front-load any actionable information and uses jargon ('UXP', 'DOM/QE', 'semantic UI fallback') without explanation. The structure offers no hierarchy or key details first.

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 6 parameters, nested objects, and no output schema, the description is severely incomplete. It does not explain the approval workflow (despite approvalId and operationId), what operations can be invoked, what search results look like, or how the risk-gating works. An agent cannot safely or correctly call this tool based on the description 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 carry the burden of explaining parameters. It says nothing about actionId, args, target, approvalId, operationId, or expectedRevision. The agent is left with zero semantic guidance for filling the required actionId or optional fields, making parameter usage entirely guesswork.

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 pair ('Search or invoke') and names a resource category ('official UXP, safe legacy DOM/QE capabilities, and semantic UI fallback'), which distinguishes it somewhat from the sibling tools that target specific domains. However, it remains vague about what 'search' and 'invoke' actually produce or accept, and it does not explicitly differentiate itself beyond being a generic 'one surface.'

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 the siblings. It mentions 'one risk-gated surface' but does not explain when that surface is appropriate, when to prefer it over premiere_project or premiere_timeline, or what 'risk-gated' entails. There is no mention of alternatives or 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?

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's use of 'Report' is consistent with a read-only operation. However, the description adds no behavioral detail beyond that—no mention of performance, side effects, what happens on missing permissions, or interpretation of the reported boundaries. With limited annotation coverage, the description carries little extra load and fails to illuminate 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 sentence, which is concise in length, but it is a dense list of undefined terms with no structure or front-loading of the most salient information. It reads like a fragment, not a clear explanation, and could be improved by defining terms and stating how the optional parameter modifies the output.

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 reports a complex set of capabilities, the description is entirely inadequate. It fails to explain the meaning of each reported element, how the 'domain' parameter influences results, or how this relates to the domain-specific sibling tools. An agent has insufficient information to decide whether to call this tool and what to expect.

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 defines a single optional 'domain' parameter with an enum list, but the description makes no mention of it or how it affects the report. Schema description coverage is 0%, so the description is solely responsible for explaining the parameter; it does not. An agent has no basis to decide which domain value to pass or what the parameter controls.

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 ('Report') and lists several report categories, but the categories themselves are undefined jargon ('enabled authorities', 'action risk', 'live-host verification boundaries') that an agent cannot interpret without additional context. It is not a tautology, but it fails to clearly convey what the tool actually provides, and it does not differentiate from sibling tools that may also report domain-specific state.

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 indication of when to use this tool versus the many sibling tools (e.g., premiere_api, premiere_timeline). It does not state prerequisites, alternatives, or conditions under which this capability report is needed. An agent would have to guess whether to call this before other tools or after.

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

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so agents know it is not a read-only operation. The description adds the credential safety property but does not disclose that invoking workflows may have destructive effects or require approval (evident from approvalId param). It fails to elaborate on expected side effects, approval flow, or the open world nature. Overall, it adds some context but misses key behavioral details.

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

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

The description is a single concise sentence, front-loaded with the core action ('Inspect or invoke'). However, it is under-specified; while concise, it omits crucial information that would make it useful. The structure is acceptable but lacks any detail or organization, so it only earns a middle score.

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 6 parameters, nested objects, no output schema, and a destructive annotation, the description is severely incomplete. It does not explain how to invoke workflows, what the parameters mean, how approvals work, or what the expected result is. For a tool of this complexity, this one-sentence description is grossly inadequate, leaving agents with virtually no guidance.

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 mentions no parameter names or their purposes. The schema contains six parameters (args, target, actionId, approvalId, operationId, expectedRevision) with nested objects, but the description provides zero mapping to these. An agent cannot infer what argument structure, target format, or operation ID mean without external knowledge. This is a critical gap.

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 purpose: to inspect or invoke approved signed-in Adobe cloud workflows. It uses specific verbs and identifies the resource domain (cloud workflows). However, it does not differentiate from sibling tools like premiere_inspect or premiere_operations, which may overlap in functionality. The 'without extracting credentials' differentiator helps, but the exact scope is ambiguous.

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 contextual guidance by emphasizing that it works with approved signed-in workflows and avoids credential extraction, which implies it should be used when credentials must remain hidden. However, it does not explicitly state when to prefer this tool over alternatives or when not to use it. No exclusions or comparisons to siblings are given, so the usage guidance is implied rather than explicit.

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

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description's 'Discover or apply' conveys both read and write behavior, which is consistent and slightly extends the annotations by signaling that some operations mutate. No contradiction. However, it discloses nothing about side effects, reversibility, or what 'apply' executes.

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 single sentence is efficient and front-loads the primary verbs. But for a tool spanning five operation categories with 6 parameters and nested objects, this reads as under-specification rather than disciplined conciseness — the brevity buys little because the content is not informative.

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 broad, high-complexity tool (6 params, nested args, no output schema, no enums, no parameter docs), the description is severely inadequate. It never explains how operations are invoked via actionId, what args/target structures look like, or what is returned. An agent cannot reliably construct a correct call.

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 carry the full burden for explaining parameters. It explains none of them — actionId, args, target, operationId, approvalId, and expectedRevision are all undocumented in both the schema and the description, including the two nested objects (args, target). Critical gap.

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-resource combo ('Discover or apply ... effects, parameters, keyframes, transitions, and audio operations') that distinguishes it from media/project/export siblings. However, it is an extremely broad umbrella claim spanning five separate domains and could overlap conceptually with premiere_operations, so differentiation is weak.

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 any of the twelve siblings. It does not name alternatives, state exclusions, or indicate which of its many operation types should route here vs to premiere_timeline, premiere_media, or premiere_operations. An agent gets no decision support.

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

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

Annotations already declare destructiveHint=true and readOnlyHint=false, which establishes the tool is a mutation. The description adds the term 'confirmed' which hints at an approval or validation step, but it does not specify what gets destroyed, whether permissions are required, or what the side effects are. Given the annotations cover the core destructive nature, the description adds a small amount of extra context, though it remains thin.

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, compact sentence with no fluff or redundant phrasing. It front-loads the verb and primary resource. It is appropriately sized for the amount of information it conveys, even though that information is minimal.

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 six parameters, nested objects, no output schema, and zero parameter descriptions, this tool is complex. The description provides only a broad purpose and fails to explain the workflow, required identifiers, confirmation process, or expected behavior. It is wholly inadequate for an agent to invoke the tool 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 input schema provides no parameter meaning. The description does not compensate by explaining any parameters, such as actionId, args, target, approvalId, operationId, or expectedRevision. It only lists export types, which could relate to actionId values but not explicitly. With no parameter information anywhere, the agent cannot correctly construct a call.

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 a resource ('export actions') and enumerates export types (frame, sequence, interchange, AME). It is not a tautology and clearly indicates the tool's domain, distinguishing it from other premiere tools that are not export-specific. However, it does not explain what 'confirmed' means or what constitutes an export action, so it is slightly vague.

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 offers no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply states the action without context about the workflow or how this tool fits among sibling tools like premiere_operations or premiere_api. The agent is left to infer usage.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds 'bounded' and the scope (host/project/sequence) but doesn't clarify what 'bounded' means or any other behavior. No contradiction with annotations, but limited added value beyond them.

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 fluff or redundant words. It's efficient and front-loaded with the core idea, though it may be too terse given the tool's complexity.

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 six parameters, nested objects, no output schema, and zero description coverage, this description is incomplete. It fails to explain what an 'inspection action' is, what arguments are required, or what the result will be.

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 by explaining parameters. It does not mention actionId, args, target, or any other parameter, leaving all six parameters semantically opaque.

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 identifies the tool as running a read-only inspection on host, project, or sequence context. However, it doesn't differentiate from sibling tools like premiere_project or premiere_media which may also perform inspections, so it lacks sibling 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?

There is no guidance on when to use this tool versus alternatives. No sibling references, no conditions, and no exclusion criteria are provided, leaving the agent to guess.

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

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

Annotations already communicate that the tool is not read-only and can be destructive (readOnlyHint=false, destructiveHint=true), so the description is not required to repeat that warning. However, it adds little behavioral context and does not explain what might be changed or destroyed beyond naming action categories.

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: one sentence, front-loaded with the action and resource. It avoids filler, though 'typed' is jargon that could be replaced with a more useful qualifier.

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 six-parameter schema, no output schema, nested objects, and destructive annotation, the description is far too skeletal. It does not explain the actionId dispatch, target/args contract, or how this tool relates to the broader Premiere tool family.

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 6 parameters including required actionId, plus nested target/args objects, but the description mentions none of them. With schema coverage at 0%, the description provides no practical help for selecting or filling parameters correctly.

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

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

The description identifies concrete action categories for a media resource: import, relink, proxy, and metadata. This makes it distinguishable from sibling tools like premiere_export or premiere_effects_audio, though the term 'typed' is unexplained and the specific outcome is vague.

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 guidance is provided. The description does not mention alternatives, prerequisites, exclusions, or when to prefer a different Premiere tool such as premiere_inspect, premiere_export, or premiere_capabilities. The reader must infer that it is for media operations.

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?

Only the openWorldHint false annotation is present, which does not disclose behavioral traits. The description mentions 'apply' and 'cancel' but gives no details on side effects, destructive potential, state persistence, or boundaries of cancellation/undo. Without readOnlyHint or destructiveHint, agents cannot infer safety or consequences, and the description does not compensate.

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, but it is overloaded with ambiguous clauses and not well-structured. The leading phrase 'Preview and confirm R2/R3 work' is confusing and not front-loaded with actionable information. It fails to prioritize clarity over brevity, making it hard to parse quickly.

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 3 parameters, a required enum, nested objects, no output schema, and zero schema descriptions, the description is wholly inadequate. It does not explain the meaning of each mode, parameter dependencies, return values, or any operational context. Agents cannot reliably invoke this tool based on the provided information.

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

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

Schema description coverage is 0%, and the description does not explain any parameters. The mode enum values (preview, apply, status, cancel, undo) are named but not elaborated on—e.g., which modes require 'request' or 'operationId' is not specified. The description adds no meaning beyond the raw schema, leaving agents without essential usage information.

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 lists several actions (preview, confirm, apply, inspect, report) but does not state a clear primary verb or resource. The phrase 'R2/R3 work' is cryptic and likely refers to some internal workflow not explained. It does not distinguish this tool from siblings like premiere_inspect or premiere_api, making the tool's purpose ambiguous.

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 versus the many sibling tools. It does not mention any exclusions or conditions for selecting this tool over alternatives. The description implies it handles operation lifecycle tasks, but the precise circumstances for calling it are left to inference.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=true, and the description's 'invoke' aligns with this. However, the description adds no further behavioral context—no details on side effects, what might be destroyed, required permissions, or rate limits. With annotations present, the bar is lower, but the description still fails to add value beyond what annotations state.

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, and the two primary actions are front-loaded. It is concise and efficient, though the brevity contributes to its vagueness. It earns a high score for conciseness, but the structure does not aid clarity beyond that.

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 6 parameters, nested objects, no output schema, and a destructive annotation, the description is severely incomplete. It does not explain the semantic plugin adapter, expected parameters, invocation patterns, return formats, or any usage details. An agent would have no idea how to call this tool correctly, making the description inadequate for the tool's 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%, and the description does not mention any parameters (actionId, args, target, etc.). It provides no meaning for the required actionId or any of the optional fields. The description entirely fails to compensate for the absence of parameter documentation, leaving the agent without any information to construct valid calls.

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 two distinct verbs and resources: 'inventory installed effects/extensions' (read) and 'invoke a versioned semantic plugin adapter' (write/execute). It clearly identifies the domain (plugins/effects) and differentiates from the immediate naming. However, it does not explicitly distinguish itself from sibling tools like premiere_capabilities or premiere_operations, so it's clear but lacks sibling differentiation.

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 two possible actions but does not provide any guidance on when to use this tool versus alternatives, nor any prerequisites or exclusions. It does not name sibling tools or specify conditions that would lead an agent to prefer this tool over others. For a tool with a broad scope, this is a significant gap.

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

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

Annotations already declare destructiveHint=true, but the description adds nothing beyond that. It does not disclose what gets destroyed, any side effects, required permissions, or error behavior. Since annotations cover only the single destructive flag, the description carries a heavy burden and fails to provide any additional behavioral context. No contradiction exists, but there is zero added value.

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, which is concise in length, but that brevity comes at the cost of clarity. It is under-specified rather than efficiently packed with information, so it does not earn its place by adding 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?

For a tool with 6 parameters, nested objects, a destructive hint, and no output schema, the description is completely inadequate. It provides no overview, no parameter guidance, no usage scenarios, and no expectations about return values or side effects. An agent cannot safely or correctly invoke this tool based on the given definition.

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 the 6 parameters (actionId, args, target, approvalId, operationId, expectedRevision) but does not mention any of them. An agent has no idea what values to provide, what the object types for args and target mean, or the purpose of the IDs and revision fields. This is a severe gap.

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 verb ('run') and a resource ('typed project lifecycle action'), but 'typed' is undefined and no specifics are given about what actions are available or what a lifecycle includes. It does not help distinguish this from siblings like premiere_operations or premiere_api, so an agent cannot tell what this tool uniquely does.

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 on when to use this tool, when not to use it, or any mention of alternative tools. The description gives no context for selecting it over the many premiere_* siblings, so the agent is left without decision support.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false, which the description does not contradict. However, the description adds little else about behavioral specifics, such as side effects, approval requirements (though approvalId is a parameter), or how 'advertised action' behaves. The phrase is cryptic and may confuse agents. Given annotations carry the baseline, this description adds minimal transparency.

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, which is concise, but it is not effectively structured since it introduces an undefined concept ('advertised action') and omits needed details. It is appropriately brief but fails to prioritize the most useful information, making it less usable than it could be.

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 six parameters, nested objects, no output schema, and no parameter descriptions, this tool is complex. The description provides only a vague overview and does not explain how to specify actions, what args/target represent, or how approval works. This is far from complete for an agent to call correctly, even with annotations present.

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

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

Schema description coverage is 0%, so the input schema provides no parameter explanations. The description fails to compensate: it mentions 'graphics, transcripts, and captions' but doesn't map these to any of the six parameters (actionId, args, target, approvalId, operationId, expectedRevision). An agent has no clue what actionId or args mean in this context, leaving the parameters entirely 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 tool 'Inspect or change graphics, transcripts, and captions', which gives a verb and resource type, but the phrase 'through an advertised action' is vague and unexplained. It doesn't clearly differentiate this from sibling tools like premiere_timeline or premiere_media, which may also involve graphics or media elements. Overall, the purpose is partially clear but not sharp 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?

No explicit guidance is provided on when to use this tool versus alternatives. The description mentions the resource types (graphics, transcripts, captions), which implies a context, but lacks any exclusions, prerequisites, or comparisons to siblings. An agent would have no way to decide between this and other premiere_* tools without deeper investigation.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description's 'Run' adds little. It does not disclose any specifics about side effects, what gets modified or destroyed, permission requirements, or whether the action is reversible. With no annotation-provided detail beyond the hints, the description carries the burden and fails to elaborate.

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 extremely short, but it is under-specified rather than concise. It front-loads nothing useful and every word is generic. A well-structured description would lead with the core purpose and then explain parameters or usage; this provides neither.

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 destructive hint, open-world hint false, six parameters with nested objects, and no output schema, the description is drastically incomplete. It does not explain what actions are available, how to construct targets or args, or what the expected response is. An agent would have almost no basis to call this tool correctly without external documentation.

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%, meaning the description must compensate for the six parameters, including actionId, args, target, approvalId, operationId, and expectedRevision. The description mentions 'typed ... action' but gives no explanation of what actionId should contain, how args/target are structured, or when approvalId/operationId are needed. An agent cannot infer how to populate parameters from this text.

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 verb ('Run') and lists a set of resource types ('sequence, track, clip, selection, marker, or transition action'), but the meaning of 'run' and the nature of these actions is entirely unspecified. It does not distinguish itself from sibling tools like premiere_project or premiere_media, which likely also involve executing operations. The scope is too broad and generic to give an agent a clear idea of what this tool actually does.

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 on when to use this tool versus the many sibling tools. No mention of conditions, prerequisites, or alternative tools. The description provides zero context for an agent to decide if this is the right tool for a given task.

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 provide readOnlyHint=false and destructiveHint=false, which are neutral but not contradicting. The description says 'control,' implying mutation, but it fails to disclose any side effects, permissions required, or the nature of changes (e.g., what gets modified, whether actions are reversible). No behavioral specifics are added beyond the annotations, which is insufficient for a tool that can alter state.

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, achieving maximum conciseness. The purpose is front-loaded with the verb and categories. However, the brevity comes at the cost of critical detail, making it structurally simple but not sufficiently informative. It scores high on efficiency but not on content.

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

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

Given the complexity (6 parameters, nested objects, no output schema, no enums, and zero parameter descriptions), the description is woefully incomplete. It does not enumerate supported actions, explain how to construct arguments, or indicate the return format. An agent would have no way to correctly invoke this tool beyond guessing. The description needs to compensate for the schema's lack of detail, but it provides only a high-level overview.

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 schema description coverage at 0%, the description carries the full burden of explaining parameters, but it does not mention actionId, args, target, approvalId, operationId, or expectedRevision at all. It gives no hints about what values actionId should take, how args and target are structured, or what these objects represent. This is a critical gap for a tool with 6 parameters including nested objects.

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 ('control') and broad resource categories ('workspace, playback, panel, and history actions'), giving a general sense of purpose. However, it lacks specificity about what specific actions are supported and does not differentiate from sibling tools like premiere_operations or premiere_timeline. It is more than a tautology but stops short of a precise definition.

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

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

The description provides no guidance on when to use this tool versus its siblings (e.g., premiere_timeline, premiere_operations). There is no mention of context, prerequisites, or alternative tools. The agent is left to infer when 'workspace, playback, panel, and history actions' are needed without any routing hints.

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