MaxVideoAI

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

Beyond readOnlyHint/destructiveHint, it explains that estimates do not reserve price or authorize generation, notes environment pricing differences (staging vs production), describes how technical failures follow the job and refund state, and clarifies that creative attempts are billable while technical failures are not – all critical safety and side-effect context.

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 long (~300 words) but every sentence carries meaning – usage triggers, exclusions, parameter conditions, and behavioral caveats. It is front-loaded with the core function and organized from general to specific, with no fluff, though it could be tightened slightly.

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

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

For a read-only estimation tool, it covers prerequisites (get_model_details), environment differences, parameter constraints, and exclusions. It omits explicit return-format details, but the absence of an output schema and the tool's purpose make the expected response (an estimate) inferable.

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

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

Schema coverage is 100% already, but the description adds actionable conditional logic: omit settings.audio when not optional, omit aspectRatio when mode.aspectRatios is empty, and separate base production from creative-attempt allowance. These go beyond the schema's declarative descriptions and help the agent construct valid requests.

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

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

The description opens with a precise statement of purpose: 'current pricing estimates of concrete video production proposals.' It names specific scope (single- or mixed-model shots, clip counts, creative attempts) and explicitly lists non-uses ('invent the creative plan', 'reserve a price', 'create a generation quote', 'inspect the wallet', 'spend funds'), which clearly distinguishes it from generation and wallet tools.

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

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

It starts with 'Use this when' providing a clear trigger, and gives explicit exclusions. It advises comparing proposals on the same assumptions before calling an alternative cheaper/lower-cost, implying there are other pricing tools, though it doesn't name them. It also directs validation via get_model_details, which orients the agent to prerequisites.

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

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

The description goes far beyond annotations by disclosing that it contacts an external provider, consumes funding, that refunds do not restore authorization, and that a confirmation is consumed even on failure or refund. It also aligns with idempotentHint by noting duplicate delivery returns the existing job, adding meaningful behavioral context not present in 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 dense but every sentence carries critical information: preconditions, financial implications, idempotency, recovery. It is front-loaded with the most important usage rule and organized logically from precondition to consequences. No filler or redundancy.

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

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

For a tool with financial and external side effects, no output schema, and high complexity, the description covers all essentials: when to call, what it does, what happens on duplicate, refund, failure, and how to recover. It even notes that an accepted job is not a completed result, ensuring the agent understands the full lifecycle.

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. It references quoteId as the 'exact fresh quote returned by prepare_generation' and implies confirmed must be true via 'explicit user approval'. While it doesn't name the parameters directly, it gives functional meaning to the quoteId and the confirmation flag, adding value beyond the schema's UUID and const true.

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 (confirm a generation), the exact precondition (after explicit user approval of the exact fresh quote from prepare_generation), and distinguishes it from siblings by specifying it consumes funding and authorizes exactly one paid attempt. It also clarifies that duplicate delivery returns an existing job, so it's clearly not a retry 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?

It explicitly says 'Use only after explicit user approval' and details when not to use it (never to retry a failed generation). It even recommends recovery paths through get_generation_status or list_recent_generations for ambiguous responses, giving clear when/when-not and alternatives.

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

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

Beyond the annotations, the description discloses key behavioral traits: the handoff is short-lived, it is not proof of upload completion, and it fails or can be denied. It also states what the operation does not do (does not start generation or modify an existing asset), adding safety context beyond the basic destructiveHint/readOnlyHint flags.

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 long, but nearly every sentence carries operational value: when to use, fallback behavior, local-file guidance, safety cautions, and failure handling. It is front-loaded with the primary use case, though the density of caveats makes it less immediately scannable than it could be with light structuring.

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

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

For a single-parameter tool with no output schema, the description is unusually complete. It explains the returned browser destination fallback, the importer and helper flow, what to do after asset IDs are returned, when to call list_media, and how to behave on failure. An agent has enough context to call this tool correctly and respond to outcomes.

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 there is only one enum parameter. The description reinforces the semantics by naming all supported media kinds (image, video, audio) and framing kind as the requested media type, so an agent can confidently select a value. It could be slightly more explicit about the parameter name, but the meaning is clear from context.

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

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

The description uses a specific verb and resource: it creates a short-lived handoff for private image, video, or audio reference media. It also distinguishes itself from related tools by explicitly noting it does not start generation or modify existing assets, so an agent can separate it from list_media and generation-oriented 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 description gives an explicit trigger condition: use it when the host cannot expose a file handle. It also provides concrete guidance for local files in Codex or Claude Code, including creating one link per file and using the packaged helper, plus a clear post-upload workflow with list_media. This is actionable and goes well beyond a generic statement.

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

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

Annotations are all default false values, so the description carries the full behavioral burden — and it delivers: it discloses the invalidation of the old quote, states that payment is not taken by the tool, and establishes that funding is not generation approval. The disclosed invalidation creates a mild tension with destructiveHint: false, but the side effect is openly declared so the agent is fully informed and no contradiction is flagged.

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?

Front-loaded purpose followed by dense, safety-critical guidance; roughly 130 words with every sentence carrying operational weight. Slightly long for a one-parameter tool, but the workflow and prohibition content justifies the length.

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?

Comprehensively covers the trigger, side effects, non-actions, follow-up workflow, and the explicit approval gate for a tool with one parameter and no output schema. The main gap is the response shape — it references 'the exact returned destination' but never describes what the tool returns beyond a destination.

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 never names quoteId explicitly, though the 'exact prepared quote' framing makes the parameter's referent inferable as the quote that needs credits. For a single required parameter this is adequate compensation, but it relies on inference rather than an explicit mapping.

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 and resource — creates a short-lived MaxVideoAI web handoff and invalidates the old quote — prefixed with the trigger condition 'when an exact prepared quote needs more credits.' This clearly differentiates it from siblings such as create_reference_upload_link and prepare_generation, whose purposes are not payment top-up handoffs.

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?

Opens with an explicit 'Use this when' trigger and later names the required follow-up sequence (get_account_status, then a fresh prepare_generation or prepare_audio_generation for Audio). It also gives explicit exclusions and prohibitions: never collect payment data, never claim the browser step completed, and never auto-retry or generate.

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 mark it read-only and non-destructive; the description adds behavioral boundaries beyond that by stating it must not reveal private email, collect payments, charge credits, change the wallet, or generate media. It does not describe response shape or potential limitations, but the added exclusions are meaningful.

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 front-loaded sentences: the first enumerates triggering intents, the second enumerates exclusions. Every clause earns its place, and there is no redundant restatement of the title.

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 parameters, read-only annotations, and a clear enumeration of returned data (account, balance, trial state, spending limits, destinations), the description is sufficient for an agent to invoke and interpret the tool correctly. The only mildly opaque term, 'safe account destinations,' is a minor domain detail.

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

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

There are zero parameters and schema coverage is 100%, so the baseline is 4. The description does not need to explain parameters; it adds value by enumerating the account-related data points an agent can expect.

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

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

The description names a clear resource (MaxVideoAI account) and the exact data the tool exposes: connected account, credit balance, trial state, spending limits, and safe account destinations. It also distances itself from sibling tools by excluding media generation, so an agent can distinguish it from get_generation_status and list_media.

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 an explicit trigger condition ('when the user asks which MaxVideoAI account is connected...') and an explicit do-not-use list covering private email, payment details, charging credits, wallet changes, and media generation. This leaves no ambiguity about when to select this tool over alternatives.

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

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds practical behavioral context: the URL is short-lived, requires generation completion, and is ownership-scoped. No contradiction with 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?

A single, front-loaded sentence with no filler. Every clause contributes meaning: source context, action, freshness, scope, and ownership constraint.

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

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

For a single-parameter tool with an output schema and strong annotations, the description covers the key constraints: where to call it, what it returns, and what prerequisites apply. The only minor gap is not explicitly naming jobId as the generation ID, but this is easily inferable.

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

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

The input schema provides only a bare jobId string with no descriptionholistically, and schema description coverage is 0%. The description implies jobId refers to a generation ('one completed owned generation') but never explicitly explains that jobId is the generation identifier, leaving some inference to the agent.

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

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

The description clearly states a specific action: create a fresh short-lived attachment URL for a completed owned generation. It distinguishes this from sibling tools like get_generation_status, prepare_generation, and present_generation by naming the exact resource and outcome.

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 clear context: use it from the MaxVideoAI result app and only for completed owned generations. It does not explicitly name alternatives or when not to use it, but the context is sufficiently directive.

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=true and destructiveHint=false, and the description reinforces this by saying it returns "safe current status" and does not expose prompts, provider details, or private media. It also adds important behavioral context: accepted/running jobs are not complete, retries have timing requirements, replacements are paid, and refund state should be checked after technical failure.

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

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

The description is front-loaded with the core use case and then adds dense, operational guidance. Every sentence carries meaningful behavioral or routing information, and there is no filler or repetition beyond what is necessary for safe use.

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?

Despite having no output schema, the description explains the important parts of the response: current status, failure/refund state, destinations, and retry instructions. It also covers post-success behavior with present_generation and accounts for Audio jobs. For a single-parameter read-only status tool, this is complete enough for an agent to act correctly.

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

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

The schema describes only jobId with min/max length, and schema description coverage is 0%. The description implies that jobId must refer to a known owned generation and mentions ambiguous submission responses, which hints at where the ID comes from. However, it never explicitly states how the jobId is obtained or validated, so the agent must infer the source from context.

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

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

The description clearly states a specific purpose: follow or recover one known owned generation, including after interruption or ambiguous submission. It also distinguishes the tool from sibling present_generation by explaining when to use that tool instead, and from list_recent_generations by focusing on a known single job.

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 explicit usage rules: use for recovery/polling, wait at least retry.afterSeconds before retrying, stop polling when retry is null, avoid repeated checks, do not resubmit on technical failure, and use present_generation once the job is complete. This is strong, actionable guidance that also warns against common misuse.

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?

Beyond the readOnlyHint annotation, it discloses important behaviors: only live generation-enabled modes are executable, required references must be private MaxVideoAI assets, aspectRatio and audio settings have specific omission rules, and empty promptingSources should be reported as absent rather than invented. These are practical behavioral traits an agent cannot infer from annotations or the simple input schema.

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 opening sentence is strong and front-loaded, but the description becomes a dense single-paragraph dump of mode semantics, asset rules, and generation guidance. Much of this is valuable, but the t2v/ref2v/v2v taxonomy could be condensed or moved to an output schema or separate reference; it is more verbose than strictly necessary.

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 output schema, the description carries the burden of explaining return-value semantics, and it does so extensively: mode classification, asset requirements, aspect ratio and audio handling, promptingSource behavior, and execution boundaries. It lacks precise detail on what 'evidence' covers, but overall it gives an agent enough context to invoke the tool and interpret common results.

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 single `id` parameter is already fully documented in the schema as 'Exact public MaxVideoAI model ID returned by list_models or recommend_models'. The description adds 'one known public' but does not meaningfully enhance the parameter's meaning, so the baseline 3 for high schema coverage applies.

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

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

The opening sentence precisely states the resource ('one known public MaxVideoAI model') and what it returns ('exact current capabilities, limits, evidence and reviewed official promptingSources'). It also differentiates this tool from list/recommend siblings by requiring a known model, and explicitly rules out pricing and generation use cases.

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 a clear when-to-use condition ('when the user needs exact current capabilities...'), practical timing ('before budgeting or quoting'), and explicit exclusions ('Do not use this for exact pricing, generation, hidden models, or provider guarantees'). It does not name a specific sibling tool as the alternative, but the schema's mention of list_models and recommend_models provides some routing context.

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

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

Annotations already indicate readOnly=false, idempotent=false, and destructive=false, but the description adds meaningful behavioral context: it owns reference management, returns asset IDs, preserves input order, and avoids generation or spending. It also clarifies expected failure-mode behavior on partial failure, which goes well beyond the 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 dense but every sentence carries operational value: purpose, ownership, return behavior, failure handling, prohibitions, and the alternative tool. It is front-loaded with the primary purpose and structured logically from what to do to what not to do.

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 one parameter, no output schema, and rich annotations, the description is complete enough. It covers the input source, constraints, return semantics, failure recovery, prohibited actions, and the alternative path. No critical information an agent needs to invoke it correctly is missing.

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

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

Schema description coverage is 0%, so the description must compensate. It explains the semantic meaning of download_url by saying files come from 'temporary host file handles' and warns against local filesystem paths or invented URLs. However, it does not explicitly describe file_id, file_name, or mime_type, leaving part of the nested object's meaning to inference from the schema.

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

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

The description uses a specific verb-resource pair: 'import up to eight user-authorized image, video or audio files... into the connected private MaxVideoAI library.' It clearly distinguishes this from create_reference_upload_link by naming the alternative and the condition that selects it. The scope and source of the files are explicit.

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 exactly when to use this tool, when not to use it ('do not call list_media after a successful direct import'), and which sibling to use instead ('use create_reference_upload_link instead'). It also provides concrete retry guidance for partial failures, leaving no ambiguity for an agent.

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

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

Annotations already mark the tool as read-only and non-destructive. The description adds useful behavioral context: assets are private, results are only safe metadata and controlled previews, and storage/provider URLs are not exposed. This complements the annotations without contradicting 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?

Two sentences, front-loaded with the use case and immediately followed by exclusions. Every clause adds information, and there is no filler or repetition.

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

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

Provides enough for a safe basic invocation: purpose, return type (safe metadata and previews), and exclusions. However, with no output schema and minimal parameter documentation, it leaves pagination semantics, the limit/cursor relationship, and whether kind can be omitted unresolved.

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 gives semantic meaning for 'kind' as a media-kind filter, but it does not explain 'limit' or 'cursor', pagination behavior, or the fact that the schema lists no required parameters while the description says 'required media kind'.

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

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

States the action (list) and precise resource (private MaxVideoAI reference media yielding image/video/audio asset IDs). It also explicitly disambiguates from uploads, exposing URLs, and generation, so an agent can distinguish it from sibling tools.

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

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

Opens with an explicit when-to-use condition: user needs reusable private asset IDs. It also gives clear when-not-to-use exclusions: not for uploading files, exposing storage/provider URLs, or starting generation. This provides strong selection guidance even without naming alternatives.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds meaningful behavioral context beyond annotations: all filtering fields are nullable, null must be sent when a constraint is unstated, and placeholders are forbidden. It also clarifies the data scope as public rather than private or provider-guaranteed, which is useful for invocation.

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 sentences with the primary usage guidance front-loaded)SkipHere. Every sentence earns its place: when to use, null-handling rule, and explicit exclusions. No filler or redundant restatement of the schema.

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

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

For a read-only filtering tool, the description explains scope, constraints, null semantics, and exclusions, which covers most invocation needs. There is no output schema and the description does not describe the exact return shape, but the phrase 'model capabilities' plus filter context makes the expected result reasonably inferable, leaving only a minor completeness gap.

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

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

Schema description coverage is 100%, so the baseline is 3; each parameter already has a clear description like 'or null unless the user constrained it.' The description's global instruction that every filtering field is nullable reinforces the schema but does not add substantial new parameter-level meaning beyond what is already present.

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 (list) applied to a clearly bounded resource: 'current public MaxVideoAI image or video model capabilities,' including audio and reference-image support. It further distinguishes itself by explicitly excluding generation, exact pricing, private models, and provider guarantees, so an agent can tell it apart from siblings like get_model_details or prepare_generation.

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

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

It opens with 'Use this when the user needs current public...' and closes with 'Do not use it for generation, exact pricing, private models, or provider guarantees,' giving practical selection guidance. It does not name specific sibling tools as alternatives, but the exclusions effectively route agents away from clearly different 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?

The annotations (readOnlyHint=true, destructiveHint=false) already establish the tool is safe. The description adds context beyond annotations: it mentions bounded page, same connected user, and explicitly warns not to claim completion for accepted/running jobs or to charge. This adds value and aligns with annotations. Minor gap: doesn't detail pagination or rate limits, but given annotations, this is sufficient.

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 multiple sentences, each carrying weight. It is front-loaded with the primary use case and then provides constraints and alternatives. It could be slightly more concise by shortening the first sentence, but generally it is tight and 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?

Given the tool has 4 optional parameters and no output schema, the description provides enough context to call it correctly: it explains the purpose, constraints (same user, bounded page), filtering, and follow-up. It doesn't explain return values, but that is not required without output schema. The only missing piece could be more explicit on pagination, but the term 'bounded' implies it.

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. It directly mentions the 'surface' parameter (filter by surface video, image or audio), which adds semantic meaning. It references 'bounded page' implying limit/cursor semantics. However, it doesn't explain the 'status' parameter in detail, but the overall guidance on filtering is helpful.

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's purpose: listing recent MaxVideoAI generations for the same connected user. It specifies the resource (MaxVideoAI library) and the action (list recent), and distinguishes it from siblings like get_generation_status and present_generation. The purpose is specific and actionable.

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 explicit usage guidance: when to use (when job ID lost or returning to recent work), what to do before considering a second paid submission, and alternatives (use get_generation_status for follow-up, present_generation for completed results). It also explicitly states when not to use it (do not use to generate, retry, or charge). This is exemplary.

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, and the description adds meaningful behavioral context: the result is already saved in the connected library, the tool must not invent URLs, and it should not poll, retry, confirm, or charge. It does not fully specify the exact return payload shape, but the mention of 'returned resource link and library destination' gives a useful baseline.

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 well ordered: primary purpose first, then mandatory verification, then fallback behavior, then explicit exclusions. Every sentence contributes actionable guidance and there is minimal redundancy.

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

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

For a single-parameter presentation tool with rich sibling context, the description covers the key operational aspects: verification, one-time use, UI fallback, URL safety, and persistence of the generation. The main gap is that jobId semantics are undefined, and there is no explicit return contract despite the absence of an output schema, but the description is otherwise sufficient 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?

The input schema has one required parameter, jobId, with 0% schema description coverage, so the description carries the full burden. The description never explains what jobId means, where it comes from, or how it relates to a completed generation. The parameter name is somewhat self-explanatory, but the agent is left without explicit guidance on populating it.

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

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

The description states a specific verb and resource: 'deliver a completed owned MaxVideoAI generation as inline video, image or original Audio in a compatible UI host.' It also distinguishes itself from siblings by explicitly saying 'Do not poll, generate, retry, confirm, or charge with this tool,' making it clear this is a presentation-only operation, not generation or status checking.

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 explicit when-to-use guidance: use once after completion, and verify completion first with get_generation_status or list_recent_generations. It also provides fallback behavior for incompatible hosts and names exclusions such as no retry, no confirm, and no charge, which routes the agent away from unintended 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?

Annotations only declare read-only/non-destructive; the description goes well beyond that by disclosing that output is a capability match with editorial preference, that editorial preference is not measured quality or execution certification, that a new version never inherits a family review, and by decoding returned editorialGuidance/reviewStatus/reviewedAt/rationale/provenance. It also states the mutation-adjacent constraint of not asking for placeholders and not forcing model diversity.

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

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

One dense wall of text with the usage trigger front-loaded, which is good, but it repeats the same caveat family multiple times (editorial preference is not quality; not an exact quote/generation command; recommendations are capability matches) and mixes call-time guidance with output-interpretation guidance. For an advisory tool the volume is heavier than needed and sentences blur together.

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 exists, so the description carries extra weight and does explain the key returned concepts (editorialGuidance categories, reviewStatus, reviewedAt, rationale, provenance) plus the mode-validation and budget-comparison workflow. It stops short of describing the full response shape or failure modes, leaving a small gap for a 13-parameter tool.

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

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

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter interpretation rules the schema does not fully carry: nullable constraints must be null or omitted rather than placeholder values, and only missing choices that change result or budget should be asked for. It reinforces meaning for priorities and budgetCeilingCents by routing cost questions to calculate_project_budget instead of filling lower_cost.

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

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

The opening sentence states a specific function (advise on / recommend AI video-image models for a creative goal) and distinguishes it from siblings by naming get_model_details for validation and calculate_project_budget for pricing. An agent can tell instantly that this is an advisory recommender, not a lister (list_models) or a detail lookup (get_model_details).

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?

Explicit trigger ('when the user is undecided or asks for advice'), explicit exclusion ('Do not use when the user already chose a compatible model for validation, pricing or execution'), and named alternatives with conditions for delegating to get_model_details and calculate_project_budget. It also states a hard rule: never substitute a named model without user approval.

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