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

With no annotations, the description discloses several automatic behaviors such as filename sanitization, ISO time calculation, file saving, and index update. This provides useful side-effect awareness, though it omits details on permissions, error handling, and reversibility.

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 concise, with a clear purpose sentence followed by a bulleted list of automatic tasks. The list is dense but efficient, avoiding unnecessary words.

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 13 parameters, no annotations, and an output schema that does not help input semantics, the description lacks sufficient context about how to use the tool effectively. It covers side effects but not parameter meaning or usage scenarios.

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 description does not reference any parameter names. Since schema description coverage is 0%, the agent has no explanations for fields like recipe_name, tips, source, or cook_time. The task list (e.g., 'Leerzeichen Menge/Einheit') hints at processing but does not map to specific 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 'Erstellt HTML aus strukturierten Rezeptdaten' (Creates HTML from structured recipe data), using a specific verb and resource. It also lists various processing tasks, distinguishing itself from sibling tools like get_server_version and get_recipe_prompt.

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 no guidance on when to use this tool or when to prefer alternatives. It does not mention exclusions, prerequisites, or context, leaving the agent without criteria for selection.

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 having no annotations, the description clearly indicates a read-only retrieval operation ('returns the workflow prompt'), which is the primary behavioral trait. No side effects or hidden behaviors are implied. For a simple getter with zero parameters, this level of disclosure is sufficient.

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

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

The description is a single, succinct sentence in German that immediately states the tool's function. It contains no fluff or redundancy, and it front-loads the key information in a direct and efficient manner.

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 an output schema, the description is reasonably complete. It names the exact output ('workflow prompt for recipe extraction from PDFs'), which suffices given the low complexity. It could have added a hint about the prompt's format or how to use it, but the output schema presumably covers that, so no significant gap exists.

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 score is 4. The description does not need to elaborate on parameter details, as there are none to document. It correctly implies that the tool takes no input and directly returns the workflow prompt.

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 verb 'Gibt zurück' (returns) and the resource 'Workflow-Prompt für Rezept-Extraktion aus PDFs' (workflow prompt for recipe extraction from PDFs), making its purpose unambiguous. It is easily distinguishable from sibling tools like get_server_version or build_recipe_html_tool, all of which serve different functions.

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 no explicit guidance on when to use this tool versus alternatives. It only states what it does, without any context about typical use cases, prerequisites, or when not to use it. Since there are sibling tools with overlapping domains (e.g., build_recipe_html_tool), such guidance would be valuable.

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 that while the selection is incomplete, the tool returns a hint and can be polled repeatedly. This is useful behavioral context beyond the empty schema. No annotations are provided, so this description partially carries the transparency burden.

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, no redundancy. The first sentence states the purpose, the second adds the polling behavior. Perfectly concise.

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 polling tool with an output schema, the description covers the core workflow: it retrieves results and handles the pending state. It could mention prerequisites or error cases, but the description is adequate for the tool's simplicity.

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, and the schema is empty. The description correctly omits parameter details. No parameter documentation is needed.

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 function: retrieving the result of a selection started with select_image_regions_tool. It uses a specific verb ('holt ab') and references the sibling tool, distinguishing it from other tools.

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

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

It provides usage context: call after starting a selection with select_image_regions_tool, and call repeatedly while the selection is still pending. It doesn't explicitly mention when not to use it, but the intended workflow is clear.

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 of disclosure. The description accurately describes the behavior as returning the current recipe server version, implying a read-only operation with no side effects. While it does not elaborate on output format or error handling, the output schema exists, and the simple nature of the tool makes this level of transparency adequate.

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, front-loaded sentence in German that directly states the purpose. There is no superfluous content, and every word contributes to meaning. It is appropriately sized for a trivial no-parameter tool.

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 (no parameters, no side effects) and the presence of an output schema, the description is complete. The agent has enough information to select and invoke the tool correctly without needing additional context. The description fully covers the tool's behavior within the context of its minimal complexity.

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 description does not need to explain parameter details. The input schema is empty, and schema coverage is 100% by definition. The baseline score for zero parameters is 4, and the description does not introduce any confusion.

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 function: 'Gibt die aktuelle Version des recipe-servers zurueck' (Returns the current version of the recipe server). The verb 'returns' is specific, the resource 'recipe server version' is clearly identified, and it is distinct from sibling tools like get_working_directory_tool or build_recipe_html_tool.

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

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

The description provides no explicit guidance on when to use this tool versus alternatives. It simply states what it does, leaving the agent to infer that it should be used when the server version is needed. No exclusions or alternative-referencing statements are present.

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 merely restates the tool's purpose without disclosing any behavioral traits such as side effects, return format, or error conditions. The description adds no information beyond the tool name.

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, concise sentence that immediately states the tool's function. It is front-loaded and contains no unnecessary words.

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 simple getter with no parameters and an existing output schema, the description sufficiently communicates the core functionality. However, it lacks usage context or alternative references, though the low complexity makes this acceptable.

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 score of 4 applies. There is nothing to document in the description, and the schema already covers the empty parameter set.

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 displays the current working directory, using a specific verb ('zeigt an') and resource ('Working Directory'). It is distinct from sibling tools that involve server versions, recipe prompts, image regions, selection results, and recipe HTML.

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 no guidance on when to use this tool versus alternatives or any contextual conditions. It simply states what the tool does without explaining when it should be invoked.

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 provided, the description carries the burden of behavioral disclosure. It mentions the non-blocking return immediately after GUI launch, browser-based GUI, automatic loading of first 4 images, and the need to retrieve results later. This is strong transparency, though it doesn't cover error cases or behavior with invalid image paths.

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 concise and well-structured, with each sentence serving a purpose: main action, supported formats, default behavior, non-blocking return, and result retrieval. No redundant or irrelevant 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 tool with a single optional parameter and an output schema, the description provides a complete workflow: launching the GUI, supported inputs, default loading, non-blocking behavior, and the required follow-up step. This is sufficient for an agent to invoke it correctly and know what to expect.

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 only defines image_path as an optional string without additional description. The description adds that omitting image_path loads the first 4 images from the image directory, implying it expects a file path, but it doesn't explicitly explain what image_path accepts or how it relates to supported formats (images vs PDFs), leaving some ambiguity.

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 that the tool opens a GUI for interactive selection of image regions, supported formats, and default behavior. It distinguishes itself from sibling tools by referencing the companion tool get_selection_result_tool for retrieving results.

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 the default behavior when image_path is omitted and instructs that the result must be fetched via get_selection_result_tool, defining a clear workflow. However, it doesn't explicitly describe when not to use the tool or contrast it with alternatives beyond the follow-up tool.

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