InkRoom

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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered; the description adds genuinely new behavior beyond that—the return shape (action plus summary or usage fields) and the pagination rule 'increment page only while hasMore'. It stops short of disclosing auth/permission requirements or rate limits, but the pagination and return contract are meaningful additions.

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 dense sentences with zero filler: purpose and scope first, then return/pagination contract, then alternative routing. Front-loaded and every clause carries information an agent needs.

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, yet the description enumerates the return fields (items, page, pageSize, total, hasMore) and the iteration rule. All six parameters are schema-documented, and the alternatives are named, leaving nothing critical missing for correct invocation.

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

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

Schema coverage is 100%, so the baseline is 3; the description nevertheless adds semantics the schema lacks—the conditional pagination rule tied to hasMore and the notion of a default/permitted action value. This goes slightly past restating schema fields.

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

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

States a specific verb (read) and resource (personal balance/access or paginated billing) and immediately scopes it with 'not spending authorization', which separates it from the financially-adjacent sibling spending_policy. An agent can identify the tool's function 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?

Explicitly routes the agent: 'Use spending_policy for automatic-spending limits and list_models for model prices,' and clarifies the tool is not for spending authorization. It also notes the action defaults to 'the permitted action', covering the no-arg case.

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

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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds valuable workflow behavior: preview freezes inputs and quotes cost, auto/run reuse the preview receipt, run requires approval, and interrupted executions can resume from the original receipt. It does not spell out exactly what is destructive or how the original source is preserved, 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?

The description is dense but front-loads the core purpose and then moves through alternatives and workflow details. It is appropriately sized for a complex 16-parameter tool, though the semicolon-heavy style and the phrase 'in preview' make it slightly harder to parse than 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?

For a complex editing tool with no output schema, the description covers the essential execution model: preview produces a requestId with cost/readiness, run requires approval, and execution returns task/status or nextAction. It is close to complete, though it could say more about what destructive editing means and what the original source guarantees are.

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 schema already documents all 16 parameters, including action, requestId, referenceImages, and parentImageIndex. The description reinforces the key source and preview-receipt semantics, but mostly repeats what the schema says rather than adding new syntax or format details.

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: editing one image from either referenceImages or parentTaskId. It also immediately distinguishes this from generate_image, upscale_image, and batch_generate, so an agent can identify the tool's role 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?

It gives explicit routing guidance: use generate_image when there is no source, upscale_image for dedicated processing, and batch_generate for multiple edits. It also clarifies source selection between referenceImages and parentTaskId, including parentImageIndex for multi-image parents.

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 already declare non-read-only, idempotent, and destructive behavior. The description adds meaningful context beyond them: previews quote estimatedChargePoints, run requires user approval, interrupted tasks should be resumed rather than resubmitted, and failed tasks are retried only through retryTaskId.

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 front-loaded with purpose and alternatives before the workflow details. Every sentence adds operational value for a complex 12-parameter tool, with no redundant 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 complex generation tool with no output schema, the description covers the main lifecycle, return signals, approval, and retry semantics well. It could more explicitly mention generation_status or wait_images for polling, but the essential calling behavior is 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 description coverage is 100%, and the schema already documents action, requestId, retryTaskId, and most parameters in detail. The description reinforces the requestId/retry workflow but adds little parameter meaning beyond the schema and does not discuss many fields such as size, count, model, or quality.

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, resource, and scope: 'Create one image without a source.' It immediately distinguishes the tool from derive_image, upscale_image, and batch_generate, so an agent can identify the correct sibling without inspecting schemas.

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 explicit routing guidance for source-guided edits, dedicated processing, and multiple jobs. It also explains the preview/auto/run lifecycle, approval requirement, interruption resume behavior, and retry path, leaving little to inference.

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

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the bar is lower. The description still adds real context: cancellation does not authorize a paid retry, and repeated polling is discouraged — non-obvious consequences the annotations do not convey. It stops short of describing rate limits or exactly what cancellation destroys on an in-flight task.

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?

Every sentence earns its place: purpose and return shape first, then routing to wait_images, then the polling prohibition, then the cancellation caveat. No filler and no repetition of schema detail.

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 needn't be fully spelled out, and the description still summarizes the key ones (status, images, error/settlement). Routing and cancellation caveats are covered; only ownership/auth expectations are left implicit.

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%, including an enum on action and a note distinguishing taskId from requestId/batchId, so the schema already carries the semantics. The description only reinforces the 'owned, single task' scoping; baseline 3 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?

States a specific verb set (read/cancel) and resource (one owned taskId), plus the exact return payload. It explicitly names the sibling tools it is not (wait_images, batch_generate), so an agent can route without opening a 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?

Gives explicit alternatives and conditions: wait_images for bounded waiting and image pagination, batch_generate for multiple jobs, and an explicit 'do not repeatedly poll get' prohibition. This is a complete when/when-not map.

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 and idempotentHint, so safety is covered. The description adds real value by disclosing the return shape (topic, summary, capabilities or steps, docsUrl, version metadata), which matters because no output schema exists, and by stating the call is optional. It stops short of describing size/limits of the capability matrix, so not 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?

Three sentences, all load-bearing, with the optionality caveat and return shape front-loaded. The final routing sentence is slightly compressed ('account for personal access') but still parses correctly, costing little.

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 compensates by enumerating the returned fields, and it covers the optional-use case and sibling routing. For a single-enum-parameter read tool this is essentially complete; only finer detail about the capability matrix itself is absent.

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% and the enum description already covers 'omit for the capability matrix', so the baseline is 3. The description adds topic-selection guidance beyond the schema by implying which subject areas belong to other tools (prices, account, spending), helping an agent pick a topic rather than guessing.

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: reading capability or troubleshooting guidance, and immediately scopes it as optional ('generation does not require this call'). It also names the sibling tools that own adjacent needs (list_models, account, spending_policy), so an agent can distinguish it from them without opening schemas.

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 gives the when-not condition ('generation does not require this call') and routes three concrete needs to alternatives: model prices to list_models, personal access to account, automatic-spending authorization to spending_policy. This is close to a complete routing table for the help/account/billing cluster.

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 this as read-only and idempotent, but the description adds substantial behavioral detail: scope-dependent return fields, anonymous/missing-scope behavior, pricing display differences, and the role of Preview in confirming final charges. This is unusually transparent for a read-only listing 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?

The opening sentence is front-loaded and every subsequent sentence carries useful information about access, return fields, or pricing. It is somewhat dense and run-on, but not padded.

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 must carry return-value context, and it does: it names the relevant fields and explains the publicCatalog pricing nuance. For a one-parameter read-only listing tool with annotations, this is complete enough for correct invocation.

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

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

Schema description coverage is 100%, and the single includeUnavailable parameter is already fully documented in the schema. The description does not add meaning beyond that schema detail, so the baseline of 3 is appropriate.

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 specific verb and resource: "List models, parameters and prices." It also distinguishes the tool from siblings by explicitly pointing to account for balance and spending_policy for limits.

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

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

It gives clear usage context by explaining authenticated vs anonymous behavior and naming account and spending_policy as alternatives for related but different needs. It does not explicitly state when not to use this tool beyond those alternative routes.

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/idempotentHint; the description adds that no MCP Token, model call, or credit charge is involved, that authenticated scopes are excluded, and that responses carry scope, accountAuthorization=not_evaluated, action, and either list or item. Those auth and cost disclosures go meaningfully beyond the structured 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?

Dense and front-loaded: cost/auth exemption first, then the search/get distinction, then scope limits, then return shape and exclusions. Some return-field detail duplicates the output schema, which is mild redundancy, but no sentence 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?

Given an output schema exists, the description need not spell out return fields, yet it does so briefly while still covering auth, cost, scope restrictions, and the search/get split. Nothing essential for correct invocation is missing; only the non-scope filters go undescribed.

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. The description still adds value by clarifying the omission-or-recommended constraint on scope, the id linkage to search results, and how action drives list vs item output. It doesn't document pagination or filter params (tags, group, category, keyword), so it stops short of a 5.

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

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

States a specific verb+resource (read public prompts) with two named modes, search (default) and get, and defines exactly what search returns (published, reviewed system recommendations) versus get (one public detail by id). An agent can distinguish this read-only prompt library from mutation-oriented siblings like generate_image or reverse_prompt 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?

Explicitly states search is the default, that get requires an id returned from search, that scope must be omitted or set to recommended, and that mine/favorites/private remain authenticated and out of scope. It also names what the tool will never do (generate, sync, evaluate, rewrite), which is a clear when-not-to-use boundary.

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 flag idempotency and non-destructiveness; the description adds the real behavioural payload — this is an idempotent refund/compensation path, not a regeneration, and the refund trigger set is precisely bounded by HTTP status codes. The enumerated result states (reachable, unconfirmed, refund_pending, refunded) and the pointer to settlement for amounts give the agent the side effects it must anticipate.

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-loads the purpose in four characters, then layers conditions, exclusions, and outcomes in dense semicolon-delimited clauses; essentially every clause carries new information. Slightly dense for skim-reading, but 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?

With an output schema present, return values need not be spelled out, yet the description still names the status vocabulary and where refund amounts live, so the agent knows what to expect. Combined with the explicit refund/exclusion rules, nothing material is missing for correct invocation.

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

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

Schema coverage is 100%, so taskId/resultId/imageIndex are already fully documented in the schema. The description only restates that the original taskId and imageIndex must be reused, adding marginal meaning (no new-generation taskId) beyond the schema's own wording.

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: verify/report that the original image download failed, with the exact identifiers to supply. It is clearly distinguishable from generate/derive/upscale siblings, though it never explicitly contrasts itself with the closest neighbour, generation_status, which an agent might otherwise reach 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 explicit inclusion criteria (only server-issued links, only explicit 403/404/410) and an explicit exclusion list (timeouts, transient failures, normal expiry, manual deletion, local save failures do not auto-refund), plus the instruction not to submit a new generation. That is a full when/when-not contract.

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 readOnly=false, idempotent=true, destructive=true; the description adds cost and authorization behavior (administrator-configured model, per-image price, default 2 credits), spending-policy vs approval semantics, and the fact that 'running' means background analysis where the agent should wait and follow nextAction to retrieve a free receipt without restarting. That is substantial behavior beyond the structured fields.

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 core purpose, then the cost/approval model, then the workflow and the sibling redirect. Dense and information-rich, though the middle sentences are packed close together and would read better as separated clauses.

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 four-action paid tool with an output schema, the description covers pricing, approval, resumption, and the background-running state machine — including the nextAction follow-up — so nothing an agent needs to call 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 coverage is 100%, so the baseline would be 3, but the description adds real meaning: auto/run/get accept only the original requestId, and requestId reuse avoids a new analysis. The action enum's intent is reinforced rather than merely repeated.

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 — reconstructing Chinese/English generation prompts, negative terms and visual anchors from one image — which is unambiguous and clearly distinct from sibling tools like generate_image or derive_image. It also explicitly marks its boundary against 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?

Gives per-action guidance (preview freezes and quotes, auto obeys spending policy, run needs explicit approval, get resumes a receipt for free) and states an exclusion plus alternative: 'No automatic image generation; use generate_image with a separate quote to validate.' An agent knows both when to use each action and when to route elsewhere.

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 adds substantial behavioral context beyond annotations: explicit consent requirements, default unlimited behavior for new accounts, suggested limit values, preservation of existing policies, interaction with wallet balance/token caps/permissions, revision staleness, and reservation accounting. This is rich disclosure for a destructive update-capable 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?

The description is front-loaded with the core read/update distinction, but it is a dense paragraph with multiple operational clauses. Some sentences, such as table-formatting and reservation-counting instructions, are tangential to invoking the tool and reduce conciseness.

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 destructive-update nature, rich annotations, full schema coverage, and an output schema, the description provides enough context for correct invocation. It covers consent, defaults, revision handling, and constraints that an agent needs before calling this 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 description coverage is 100%, so the schema already documents action, policy, and confirmed in detail. The description reinforces key semantics such as complete policy replacement, including unlimited and latest revision, but largely duplicates schema-level guidance rather than adding new parameter meaning.

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 read/update purpose for an account-wide spending policy, with action=get and action=update behavior made explicit. It distinguishes the two modes and names the policy object, though the opening phrase 'account-wide authorization' is slightly less direct than 'spending policy'.

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

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

It gives clear usage conditions: get reads without other arguments, update requires the complete policy and confirmed:true, and updates must only occur after explicit user consent. It also explicitly forbids autonomous limit increases, which is a strong when-not-to-use rule.

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

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

Annotations declare destructiveHint=true and idempotentHint=true, and the description adds genuinely non-structured behavior: run requires user approval, preview produces a requestId/cost/readiness receipt that auto/run reuse, and execution returns task/status and possibly nextAction. It does not explain why the operation is flagged destructive or what the approval/rate-limit flow looks like, so it falls just short of full disclosure.

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 core purpose and alternatives, then a compact workflow clause. It is information-dense with no filler, though the telegraphic 'receipt' phrasing and run-on clauses require careful reading.

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 5-parameter tool with one required param, no output schema and a destructive annotation, the description covers inputs, execution flow, approval gating, and even return fields (task/status, nextAction). What it omits is the specific consequence behind the destructiveHint and any failure/recovery modes.

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% (baseline 3), but the description adds operational meaning the schema lacks: requestId is a reusable preview receipt rather than a fresh input ('auto/run only, without new image inputs'), and action semantics tie into the preview/approval lifecycle. This is real value beyond the enum descriptions.

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 concrete verb plus resource and enumerated operations ('Apply x2/x4/anime/face to one image'), immediately distinguishing it from sibling tools. An agent can tell this is the dedicated upscaling tool 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?

Explicitly routes to alternatives: 'use derive_image for general edits and generate_image for new images.' It also explains the preview/auto/run lifecycle and that run requires approval, so the when-to-use decision is fully specified.

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?

Despite annotations already marking it read-only and idempotent, the description adds substantial behavioral detail: timeout bounds, delivery-mode preview counts, pending versus failed semantics, expiration snapshots, continuation behavior, and tool-error behavior for invalid or unauthorized lookups.

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 purpose and timeout facts are front-loaded, but the paragraph is dense and repeats failure semantics: pending is not failure, failed tasks carry error/settlement, and failed tasks remain with error/failure and settlement. Some tightening would improve it.

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 complex wait/continuation tool, the description covers the important operational cases: bounded waiting, continuation via nextAction, pending versus failed states, expiration behavior, and invalid lookup errors. An output schema exists, so return-field enumeration is supplementary rather than necessary.

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. The description still adds meaning beyond the schema by explaining delivery-mode differences such as 6 native previews versus 32 original links, and by framing cursor as a nextAction continuation value.

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: wait for existing requestId, batchId, or taskIds, and explicitly says it never submits a new generation. It distinguishes the tool from generation and cancellation 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?

It clearly directs the agent to await existing receipts and not submit new generation, and it names generation_status for one-task cancellation. However, it does not fully explain when to choose wait_images versus generation_status beyond the cancellation case.

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