Logospell

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds useful context about the shared account balance, enhancing understanding without contradicting structured data.

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 conveys the exact purpose with no wasted words. The description is both concise and structurally effective.

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 tool with comprehensive annotations and an output schema, the description is fully sufficient. It adds the key nuance of a shared balance, covering all contextual needs.

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 has zero parameters, so the baseline is 4. There is no parameter description needed beyond the schema, which correctly shows an empty object.

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?

Description clearly states the tool checks remaining image generation credits, with specific verb 'Check' and resource 'credits'. The added detail about shared balance between MCP calls and the generate page distinguishes it from sibling generation 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?

The context makes it obvious this is for verifying available credits before generation, but no explicit when-to-use or alternative comparisons are given. Since no sibling performs the same function, this is not a significant gap.

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

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

The description discloses extensive behavioral details beyond annotations: the upload URL and ref_ token workflow, the out-of-band HTTP PUT mechanism, the per-key privacy and rolling expiry window, cost implications, and the explicit rationale against embedding base64 in JSON. This is far more transparent than the minimal annotations.

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

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

The description is a single dense paragraph but well-structured, moving from purpose to mechanics to constraints. It is slightly longer than necessary—some rationale (e.g., base64 context pain) could be trimmed—but every sentence contributes to operational understanding, so it remains efficient.

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 description covers all essential context: return values, prerequisites (image format/size limits), the upload mechanism, the alternative shortcut, privacy/expiry behavior, and cost. Given the output schema exists and the description explains what is returned, it is fully complete for an agent to invoke 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?

While the schema covers parameter descriptions at 100%, the description adds meaning by explaining how sourceGeneration and sourceImage work together, that sourceImage is downscaled to fit, and that these parameters are the shortcut path that skips uploading. It also clarifies the token-based interaction with other tools' parameters.

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: 'Create an upload slot for a reference image.' It clearly distinguishes itself from siblings by stating 'This is the ONLY way to supply reference images,' making it unmistakable which tool to invoke for this purpose.

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 guidance on when to use the tool versus alternatives: it is the only way to supply reference images, and when using one's own recent generations, the description directs to skip the upload and use sourceGeneration/sourceImage instead. It also notes the edge case of needing to resize images before uploading.

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 well beyond the annotations by disclosing cost per call, return format (zip URL with image, prompt.json, index.html), short-lived download URL, no-template prompt handling, rejected prompts, max length, and rate-limit behavior. There is no contradiction with 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 long but every sentence carries necessary information. It is well-organized with lead purpose statement, sibling disambiguation, pixel-size table, format notes, and a final error-handling rule. The structure makes it easy for an agent to extract sizing and concurrency constraints.

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 seven parameters, an output schema, and operational constraints, the description is remarkably complete. It covers when to use, what to return, accepted dimensions and formats, prompt limits, implementation requirement around unpackTo, and rate-limit behavior. The agent has everything needed to invoke this tool correctly.

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

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

Even though schema coverage is 100%, the description adds meaningful operational detail: the exact supported width/height pairs, to keep pixel size out of the prompt, the quality default of 90, the filename default, and the unpackTo/download behavior. This goes well beyond the schema's own parameter 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?

The description uses a specific verb and resource: 'Generate a single composed illustration from a prompt' and explicitly lists example outputs like scene, environment, hero image, banner, and character portrait. It also distinguishes itself from siblings by directing set-based use cases to generate_image_set or generate_transparent_image_set, leaving no ambiguity about scope.

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 states when to use this tool versus alternatives: single composed illustration here, sets of separate subjects in generate_image_set or generate_transparent_image_set. It also gives operational guidance: run generation calls sequentially, never in parallel, and wait the suggested seconds when a rate-limit error is returned.

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 beyond annotations, which only indicate readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. It explains behavioral traits such as consuming 1 credit per call, the need for sequential execution (only one generation at a time per API key), the possibility of rate limit errors and recommended response, the short-lived zip URL that requires immediate download, and the validation flow with 'skip' and 'auto-apply'. It also details the native resolution behavior and size effects. This is comprehensive transparency that contradicts nothing in 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 long but well-organized with clear sections (style rules, size considerations, error handling). It is front-loaded with the core purpose and usage, then details. While every sentence is informative, the length is substantial; however, given the complexity of the tool, the thoroughness is justified. Minor redundancy exists (e.g., repeated advice on style-text-plus-references), but overall it's structured effectively.

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 10 parameters, a complex validation flow, and an output schema (zip URL), the description is exceptionally complete. It covers parameter syntax, constraints (max 18 images, character limits, size ranges), common pitfalls (framing, backgrounds, connections), and interaction with sibling tools (create_reference for styleReferences). The output schema likely explains the zip structure, but the description also notes the download URL is short-lived, adding necessary context. The description leaves no obvious gaps for an agent to misuse the 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?

Although the schema already has 100% coverage, the description adds significant semantic value beyond the schema. For example, it explains the trade-offs of omitting size (native resolution, higher quality, but varying dimensions) versus specifying size (consistent dimensions but potential softening), and it clarifies the interaction of style and styleReferences for maintaining style consistency. It also warns about phrasing that can lead to unwanted framed compositions. This goes well beyond the schema's 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?

The description clearly states the tool's purpose: generating a cohesive set of custom images on a solid-color background, each a separate isolated subject sharing one style. It distinguishes itself from siblings by explicitly naming alternative tools: generate_transparent_image_set for transparent backgrounds and generate_illustration for single composed scenes or full-bleed images. This meets the highest standard for purpose clarity.

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 when-to-use guidance: it says to use generate_transparent_image_set for transparent backgrounds, generate_illustration for single composed pictures or scenes, and generate_image_set for sets of isolated subjects. It also gives operational guidelines like running generation calls sequentially, never in parallel, and advice on handling rate limits. These explicit exclusions and alternatives score a 5.

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 minimal annotations (readOnly=false), the description discloses credit cost, zip URL return, sequential generation constraints, style-check behavior, rejection rules, and failure modes like framed canvases or connected subjects. It also tells the agent how to handle style-check suggestions and resubmission with validation='skip', well beyond what the annotations convey.

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 front-loaded: core purpose, use-case alternatives, cost, and sequencing come first, followed by a structured rule list. There is some redundancy with schema text (size range, 'style must describe a visual style'), and the prohibition list is extensive, but each rule targets a distinct failure mode, so the length is largely earned.

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 9-parameter tool with an output schema, the description is functionally complete: it covers return delivery (zip URL), pricing, concurrency, validation states, reference-image workflow, and every constraint needed to compose a valid call. No obvious gap would cause an agent to misinvoke.

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 already 100%, but the description adds substantial parameter-level meaning: how to split HOW vs WHAT across style and subjects, prohibitions on background/color-field phrasing, maximum 18 subjects, character limits, size range, and the required workflow for unpackTo (download immediately). It also clarifies validation modes and reference token usage beyond the schema 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?

The description opens with a specific verb and resource: 'Generate a cohesive SET of custom images with TRANSPARENT backgrounds, each one a separate isolated subject sharing one visual style,' and names concrete use cases (icons, logos, sprites, UI assets). It explicitly distinguishes itself from siblings: 'When a solid colored background fits... generate_image_set...' and 'For a single composed scene... use generate_illustration instead.'

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 and alternatives: solid-color backgrounds point to generate_image_set, single composed scenes point to generate_illustration, and extending an existing set is covered via styleReferences. It also instructs operational sequencing ('Run generation calls sequentially, never in parallel'), rate-limit handling, and the validation workflow with suggest/skip/auto-apply.

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 significant behavioral context beyond the annotations: it clarifies that re-listing does not extend expiry, that generations from the web page appear, that it costs no credits, and that lineage data is included for reuse. These are specific, non-obvious details that help the agent understand side effects and limitations. The annotations already declare readOnlyHint and idempotentHint, and the description reinforces without contradicting.

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 logically structured: it opens with the core purpose, then adds the recovery use case, then explains billing and expiry behavior, then lists return fields, and ends with cost. Every sentence adds useful information, but it is longer than strictly necessary. It's efficient without being bloated, so a 4 is fitting.

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

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

Given the tool's simplicity (one optional parameter), the presence of an output schema, and thorough annotations, the description covers all essential context: the exact data returned, the ordering, the inclusion of web-generated items, the inefficiency of re-listing for extending expiry, and that it costs no credits. There are no gaps that would leave an agent uncertain. This 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?

The only parameter, 'limit', is fully described in the schema (coverage 100%). The description does not add any extra semantic meaning about the limit parameter itself, but it does mention ordering ('newest first') which indirectly relates to the result set. Since the schema already covers parameter meaning, a baseline score of 3 is appropriate—the description offers no added value for parameters.

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 it lists recent successful generations and specifically mentions the use case of recovering lost download URLs. It identifies the resource (generations) and the verb (list), and distinguishes itself from sibling tools like generate_illustration by focusing on retrieving existing data rather than creating new content.

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 explicitly says 'Use this to recover a generation whose result message was lost', providing clear when-to-use guidance. It also adds important context about billing and expiry, but does not explicitly state when not to use it or mention alternative tools by name (though it references create_reference for lineage reuse). This is close to a 5 but lacks an explicit when-not statement, so I'm scoring it 4.

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