seedance-mcp

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

With no annotations, the description carries the full behavioral burden and does disclose the key trait: only queued tasks are affected, running ones are untouched. It says nothing about idempotency, behavior on an invalid or already-completed task_id, or permission requirements, leaving meaningful gaps.

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

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

Two short sentences, front-loaded with the action and followed by the limiting constraint. Every sentence earns its place with no filler.

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

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

For a single-parameter cancellation tool with an output schema present, the description covers purpose and the critical limitation adequately. The only real omission is the meaning/source of task_id, which the schema also fails to document.

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

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

Schema description coverage is 0% for the single task_id parameter, and the description adds no information about its format, where to obtain it (e.g., from list_video_tasks), or whether it accepts a full id or prefix. Low coverage should be compensated here, and it is not.

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

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

States a specific verb+resource ('Cancel a queued video task') and immediately scopes it to queued tasks, so the agent knows exactly what operation this performs versus siblings like generate_video or list_video_tasks. It stops short of explicitly naming an adjacent sibling, so a 4 rather than a 5.

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

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

The second sentence gives a clear negative condition ('Running tasks can't be stopped'), which tells the agent when this tool will not apply. It does not name an alternative path for running tasks, but the usage context is unambiguous.

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

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

With no annotations, the description carries the full burden, and it does disclose the diagnostic scope (API key validity, connectivity, approval-delivery routing), which implies a non-mutating operation. It stops short of saying whether it is purely read-only, whether it requires credentials already present, or how failures are surfaced, so the disclosure is partial.

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

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

A single compact sentence with the diagnostic target listed up front and no filler. It is as short as it can be while still naming the three things checked.

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?

An output schema exists, so return values need not be described, and the tool is a parameterless read-style check. The description covers the subjects of the check adequately; only the absence of trigger conditions and failure semantics keeps it from being fully complete.

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

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

The schema takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies, and the description correctly does not invent arguments.

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 (check) and enumerates three concrete targets: API key, connection, and spend-approval delivery path. That tells an agent this is a setup/connectivity diagnostic rather than a data-fetching tool. It does not, however, explicitly distinguish itself from the sibling spend_status, which also concerns spend.

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 statement of when to run this versus alternatives such as spend_status or preapprove_spend, nor any prerequisites or post-conditions. Usage can only be inferred loosely from the word 'check' and the setup-oriented subject matter.

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

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

No annotations are provided, so the description carries the full burden. It does disclose one important behavioral trait — no cost is incurred — but says nothing about authentication, whether the estimate is authoritative or approximate, rate limits, or how results should be interpreted before calling preapprove_spend.

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 short sentence, front-loaded with the verb and the key differentiator. No wasted words and no buried information.

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

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

An output schema exists so return values need no explanation, but the tool takes a complex array of batch line items and the description gives no guidance on shaping that input or on how model/duration/reference parameters affect the price. For a nested pricing tool this is under-specified.

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

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

Schema description coverage is 0% and the description never mentions the 'items' array, the PlanItem structure, or any of the fields that drive pricing (kind, model, duration, resolution, reference images). The nested schema defines fields internally, but the description contributes no parameter meaning at all.

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 (price) and resource (a plan) and adds the key scope qualifier 'without spending anything', which separates it from the spend/generate siblings. It does not name a specific alternative (e.g. preapprove_spend or spend_status), so it stops short of full 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?

'Without spending anything' implies a dry-run/preview usage window, which hints at when to call this rather than actually generating or spending. However, it names no alternative tool and gives no explicit when-not condition, leaving the before-vs-after-spend workflow to inference.

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

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

With no annotations, the description must carry the behavioral burden. It usefully discloses that spend-guard pricing/checking happens before generation, implying a possible rejection or approval path (matching the approval_id parameter). However it omits everything else: output location side effects (save_to), watermarking behavior, batch semantics, and failure modes.

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 tight sentences, front-loaded with the core action and cost-gate note; nothing is wasted. It is arguably too terse for a 9-parameter paid tool, but as a structure it is clean.

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?

An output schema exists so return values need no explanation, but the tool takes 9 parameters, incurs cost, and is gated by an approval flow. An 11-word description cannot make an agent confident about the approval_id/max_images/save_to interactions, leaving it materially incomplete.

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 only 56% across 9 parameters, and the description clarifies none of them. Undocumented parameters like approval_id and watermark get no explanation of their role or when they matter, so the description does not compensate for the coverage 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?

States a specific verb+resource: 'Make an image with Seedream,' which is unambiguous about the operation and the backing model. Sibling tools are all video/spend/status related, so the image-generation purpose is naturally distinguishable, but the description does not explicitly name them.

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

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

No when-to-use guidance, no alternatives, no prerequisites spelled out. The phrase 'checked by the spend guard first' hints that a cost/approval flow is involved but never names estimate_cost or preapprove_spend, nor explains when generation will be blocked.

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

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

With no annotations, the description carries the full behavioral burden. It does disclose one valuable trait — pricing and spend-guard gating happen before dispatch — but is silent on async vs blocking behavior, how 'wait' interacts with 'timeout_s', and the approval_id workflow, all of which matter for a 19-parameter generation call.

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 action and the key operational guarantee, with zero filler. It is arguably sparse for a 19-parameter tool, but every sentence earns its place.

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

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

An output schema exists, so return values need no explanation. However, for a 19-parameter mutation-style tool with no annotations, the description omits the async/blocking model, the approval flow implied by approval_id, and cost/approval prerequisites — too much is left for the agent to guess.

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 58%, so the schema already documents many parameters. The description adds real value by mapping first_frame/last_frame/reference_images/reference_videos onto the text-to-video, image-to-video, and reference-media modes, but it does not compensate for the undocumented remainder.

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 ('Make a Seedance video') and enumerates the three generation modes, which maps directly to the first_frame/last_frame/reference_* parameters. It does not explicitly distinguish itself from siblings like video_task or generate_image, so it stops short of a 5.

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

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

No when-to-use, when-not-to-use, or alternative routing is given. The mention of the spend guard hints at an approval workflow, but the agent is never told when to prefer video_task, cancel_video_task, or preapprove_spend, nor when this tool is the wrong choice.

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

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

With no annotations, the description carries the full burden. It usefully discloses ordering ('newest first') and that per-task cost is included, but says nothing about read-only semantics, pagination behavior, default page size, or result limits, which an agent needs for a paged listing.

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 compact sentence with the resource, scope, ordering, and return content front-loaded; no filler whatsoever.

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

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

The output schema covers return values and cost, so that is not a gap. However, with no annotations and four entirely undocumented parameters, the description leaves filtering and pagination behavior unexplained for an agent that must decide how to page and filter.

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

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

Schema description coverage is 0% across four parameters. The description mentions 'recent' which hints at ordering, but never explains 'page', 'page_size' (with its 100 max), or that 'model' and 'status' act as filters — a significant omission at 0% coverage.

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

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

States a specific verb and resource ('list ... video tasks'), plus scope ('on this key') and ordering ('newest first'). It clearly differs from the singular siblings 'video_task' and 'generate_video', but never names an alternative explicitly, so sibling differentiation is implicit rather than stated.

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

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

The description implies a browse-recent-history use case but gives no when-to-use guidance, no conditions for choosing it over 'video_task' (single fetch) or 'spend_status' (cost aggregation), and no exclusions or 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?

With no annotations, the description carries the full burden and does meaningful work: it discloses the human-in-the-loop requirement, the spend scope ('up to the approved dollars and number of calls'), and a concrete 3-hour validity window. It leaves gaps around idempotency, what happens on expiry, and whether calling it commits money, but the expiry and coverage-cap disclosures are exactly the behavioral traits an agent needs for a spend tool.

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

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

Two compact sentences, front-loaded with the core action and followed by the mechanism and constraint. Every clause earns its place.

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

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

An output schema exists, so return values need not be explained. For a 3-param approval tool, the description covers the two-phase flow (request then confirm) and the validity window. It could say more about failure/expiry behavior and its relationship to estimate_cost, but it is close to complete.

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

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

Schema coverage is 67% and the schema itself documents the PlanItem fields well. The description enriches approval_id semantics by tying it to downstream generate calls, which is genuinely useful. It adds nothing for 'note' or 'items', so it sits at the baseline for a partially documented 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?

States a specific verb+resource (get one human approval for a whole batch) and immediately explains what the tool produces (an approval_id). It is clearly distinguishable from the generate_* siblings because it is an approval/pre-flight step. However, it does not explicitly differentiate itself from the adjacent spend_status or estimate_cost siblings, which also belong to the pre-spend flow.

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

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

Usage is implied rather than stated: the reader infers they should call this before generate calls and then reuse the approval_id. The approval_id parameter adds a strong conditional ('only after the user said yes') that clarifies the confirm-phase. But there is no explicit when/when-not guidance or comparison to estimate_cost, which an agent would plausibly confuse this with.

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

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

No annotations are provided, so the description carries the burden. It clearly frames this as a reporting/status read, which is the main behavioral fact, but it says nothing about auth requirements, whether the period is configurable, or freshness of the data. For a zero-parameter read tool the risk surface is small, so this is adequate rather than strong.

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 tight sentence with the core value front-loaded ('what you've spent this period') and the qualifiers (by model, against budget and caps) trailing efficiently. Nothing is wasted.

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?

An output schema exists, so return values need not be explained, and the description correctly focuses on what the tool reports. It is nearly complete; only a note on the meaning of 'this period' or read-only status would close the remaining gap.

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

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

The tool takes zero parameters, so the baseline of 4 applies. There is no parameter behavior the description needs to compensate for.

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 resource and scope: current-period spend, broken down by model, measured against budget and caps. That distinguishes it implicitly from estimate_cost (forward-looking) and preapprove_spend (approval), though it never names those siblings directly.

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

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

Usage is implied by the content ('what you've spent this period'), but there is no explicit when-to-use statement or routing against the spend-related siblings estimate_cost and preapprove_spend. An agent can infer the context but must do the disambiguation itself.

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

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

No annotations are provided, so the description carries the full behavioral burden. It discloses success outputs (video_url, real cost, saved file) but omits whether the operation is read-only, that save_to causes a file write side effect, how wait/blocking behaves, and what happens on failure or timeout.

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

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

The description is two short, front-loaded sentences with no wasted words. The second sentence is telegraphic but still earns its place by summarizing successful outcomes.

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?

An output schema exists, so return values need not be explained in depth. However, with no annotations, the description leaves important behavioral context unstated—such as read-only nature, save_to side effects, blocking behavior, and error handling—making it minimally adequate for a status tool with a wait parameter.

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 50%, with task_id and timeout_s undocumented in both schema and description. The description adds no parameter-level meaning beyond hinting at 'saved file' (already covered by the save_to schema description), and does not compensate for the missing semantics of task_id or timeout_s.

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: retrieving the status of a specific video task. It distinguishes itself from siblings like list_video_tasks (plural) and generate_video (creation) by referring to a singular 'a video task', though it does not explicitly name alternatives.

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

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

There is no guidance on when to use this tool versus alternatives such as list_video_tasks or generate_video. It merely states what it does, leaving the agent to infer context from the name and required task_id.

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