CropDen: image sizes and AI image tools

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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true): 5 credits per run with refund on failure, API key requirement, input constraints of 10 MB / 2048 px on the longest side, 7-day result link lifetime, and the critical caveat that the model redraws the whole frame so fine details of the original may change. That last point is exactly the kind of non-obvious side effect an agent needs.

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?

Five tight sentences, front-loaded with the core capability, then cost, requirements, input limits, output, and the risk caveat. No filler or restatement of the tool name.

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?

Covers cost, auth, input constraints, output lifetime and the redraw caveat, which is comprehensive for a one-shot generation tool with no output schema. The remaining gap is the execution model: the presence of a get_ai_task sibling suggests tasks may be asynchronous, yet the description simply says it 'returns a link', leaving the agent unsure whether to poll.

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 enum of ratios and the image_url/image_base64 descriptions already carry most semantics; the description adds constraints not present in the schema (formats PNG/JPEG/WebP, 10 MB ceiling, 2048 px limit). It does not clarify the mutual exclusivity of image_url vs image_base64 beyond what the schema implies.

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 ('extend an image to a wider or taller shape with AI') plus a concrete use case (portrait to 16:9 thumbnail without cropping the subject). This distinguishes it clearly from siblings like ai_upscale_image and ai_remove_background, which change resolution or remove elements rather than changing aspect ratio.

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 example use case gives a clear context for when to reach for this tool, and the file-format/size limits implicitly rule out some inputs. However, it never explicitly routes the agent away from alternatives (e.g. 'to increase resolution instead, use ai_upscale_image') and does not say whether this is a blocking call or one that requires polling via get_ai_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 only declare readOnlyHint=false and openWorldHint=true, so the description carries useful extra weight: billing behavior (1 credit, refunded on failure), an auth prerequisite (API key), hard input limits, and result-link expiry of 7 days. It stops short of clarifying execution mode (synchronous return vs. a queued task needing get_ai_task), which is the one behavioral ambiguity left.

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 with the action and the result, then compactly appends cost, auth, input limits and return semantics in short clauses. No filler or restatement of the tool name.

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 correctly spells out the return value (a link valid 7 days) alongside cost, auth and input constraints. The remaining gap is the relationship to get_ai_task — an agent cannot tell whether the link is returned immediately or after polling.

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% and both parameters already document their formats and their url-vs-base64 alternative, so the baseline is 3. The description adds the 10 MB / 2048 px constraints that apply to either input, but does not explain selection between image_url and image_base64 beyond what the schema already says.

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 ('Remove the background of an image with AI') and the exact output ('a PNG with transparency'), which cleanly separates it from sibling operations like ai_extend_image or ai_upscale_image. The agent knows what it produces without opening the schema.

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 preconditions for use are covered (CropDen API key, accepted formats, size caps, 1-credit cost refunded on failure), so an agent can judge eligibility. However, there is no guidance on when to prefer this over siblings such as ai_extend_image or ai_upscale_image, and no mention of whether results must be retrieved via get_ai_task even though that sibling exists.

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?

Substantially exceeds the annotations: it discloses per-factor credit pricing, a refund-on-failure policy, the auth requirement (API key), input format and dimension caps, and a 7-day result-link lifetime. Since annotations only cover readOnlyHint=false and openWorldHint=true, this is exactly the extra context an agent needs before spending credits.

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

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

Four short sentences with the capability first, then cost, then constraints, then return value — no filler. Each sentence carries information the agent cannot get from the schema or annotations.

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 credit-charging mutation with no output schema, the description covers cost, failure handling, auth and return value well. The remaining hole is how the two mutually exclusive image source parameters are chosen between and that at least one is required.

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 description compensates by adding concrete validation rules for the inputs (PNG/JPEG/WebP, 10 MB, 2048 px at 2x vs 1024 px at 4x) that the schema omits. It also reinforces the factor enum. The one gap: it never clarifies that one of image_url or image_base64 is needed even though neither is marked required.

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?

Opens with a specific verb+resource+capability: 'Upscale an image 2x or 4x with AI.' That reads clearly against siblings like ai_extend_image and ai_remove_background, which do different transformations, so an agent can route without opening the schema.

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 prerequisites (CropDen API key), cost (8/12 credits) and input limits imply when the tool is viable, and the credit cost implicitly tells the agent to check get_credit_balance first. But there is no explicit when-to-use/when-not guidance and no direct comparison to ai_extend_image, which is the closest alternative for enlarging an image.

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 establish readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds the non-obvious behavioral fact that this is a polling tool with a recommended ~10s interval. It stops short of saying what a finished task returns or whether tasks expire, which keeps it below a 5.

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, zero filler, with the purpose front-loaded and the actionable instruction second. Nothing could be removed without losing 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?

There is no output schema, so the description must explain what comes back, and it only implies 'status' without naming the possible states or how to recognize a completed run and retrieve its result. It also omits whether polling should stop or what happens on an unknown/expired task_id.

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% and the schema only types task_id as a string, so the description carries the burden — and it does, telling the agent the value is 'the task_id it gave you', i.e. the identifier from the earlier tool response. That is meaningful provenance beyond the schema, though no format or validation detail is added.

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

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

Names the specific resource ('Status of an AI run') and the precise condition that makes the call necessary ('still working when its tool returned'), which distinguishes it from the sibling generation tools. It is not quite a crisp verb+resource statement, but an agent can immediately tell what it is for.

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

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

Gives an explicit trigger ('still working when its tool returned') and an operational instruction ('wait about 10 seconds between checks'). No alternatives are named, but among the listed siblings none compete with a status-poll, so the guidance is effectively complete.

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, so the safety profile is covered. The description adds one useful behavioral detail beyond the annotations: the balance is scoped to the API key owner (not a workspace or account). It does not disclose the return format (integer vs. object) or whether the value can be cached, leaving a modest gap.

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

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

A single short sentence with zero filler, front-loading the resource being returned and the scoping qualifier. Nothing could be removed without losing 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?

For a zero-parameter read tool with annotations covering the safety profile, the description supplies the key context an agent needs: what the number represents and whose balance it is. The only shortfall is that no output schema exists and the return shape (bare number vs. structured object) is only implied by the phrasing.

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 there is nothing for the description to explain. Baseline 4 applies, and no schema-documentation gap exists 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?

The description states a specific resource (CropDen credit balance) and narrows the scope to 'the API key owner,' which an agent can act on. It is a noun phrase rather than a verb+resource, but the meaning is unambiguous and the sibling tools (image AI operations) make the distinction obvious without further 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?

There is no explicit guidance on when to call this — no mention of checking balance before invoking paid sibling tools like ai_upscale_image or ai_extend_image, and no note on whether it can be polled freely. Usage is only implied by the tool's name and the annotations' read-only hint.

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, so safety is covered. The description adds genuine context beyond that: the data set includes safe zones, upload limits and minimum sizes, and no API key/auth is needed. Return shape is only loosely characterized, which keeps it from a 5.

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, and the capability statement is front-loaded before the invocation guidance. The long platform enumeration is slightly padded but serves to convey coverage breadth, so it largely 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?

With no output schema, the description does the work of describing what comes back: size ids in the no-arg mode, and full details including safe zones, limits and minimums otherwise. Adequate for an agent to call it correctly; a sample return shape would be the only missing piece.

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 meaning the schema does not: the zero-argument behavior (list all ids) and the distinction between passing a group id versus a platform name, with worked examples for both.

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 (exact image sizes) with concrete scope: social platforms, marketplaces, passport photos, safe zones, upload limits. This is clearly a data-lookup tool, sharply distinguishable from the AI image-editing 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?

Explicitly describes the two invocation modes: no arguments lists every size id, while `id` or `platform` returns full details. It also notes 'Free, no API key,' removing a prerequisite question. It stops short of naming when a sibling would be preferred, but no sibling overlaps this lookup function.

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