netcafe-build

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

The description directly contradicts the annotations. It says 'code is generated, deployed... you get the public URL' which is clearly a mutating, non-read-only operation, yet annotations declare readOnlyHint=true and idempotentHint=true. This is a serious inconsistency that misleads an agent about side effects.

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

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

The description is two sentences: the first packs the core value proposition and mechanics, the second hones in on fitting use cases and async behavior. Every clause earns its place, with no filler or repetition of schema details.

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 that an output schema exists (covering return values) and the description covers what the tool does, the expected output (public URL), deployment details, time-to-result, and the async handoff to check_job, this is complete for a build tool. The only major gap is the annotation contradiction, but that is scored separately.

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 baseline is 3. The description adds minor value by emphasizing that the description parameter should be 'specific about inputs/outputs' and notes language flexibility, but it does not elaborate on the other parameters (name, refine, visibility) in a way that goes beyond the schema. It meets the baseline without exceeding it.

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-resource structure: it turns a plain-language description into a live single-page web tool, with details about generation, deployment, HTTPS, listing, and public URL. This clearly distinguishes it from siblings like check_job, get_app, and list_apps, which handle job status, retrieval, and listing.

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 states 'Best for tool-style apps' and gives examples, providing clear context for when to use the tool. It also notes the async nature and directs users to poll with check_job, which is an explicit alternative. However, it does not explicitly state when NOT to use it (e.g., complex multi-page apps), so it falls short of 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?

Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: polling cadence, retry_after_seconds/next_action handling, and preference for structured_result. It doesn't contradict annotations and enriches the agent's understanding of tool behavior.

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

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

The description is two sentences long and densely packed with actionable information. It front-loads the core purpose, then provides precise polling and completion-handling instructions. No wasted 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 the simple single-parameter interface, rich annotations, and presence of an output schema, the description fully covers operational context. It explains polling behavior, terminal states, and how to handle pending vs. completed jobs. There are no critical gaps for an agent to use 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?

With 100% schema description coverage, the single parameter job_id is already well documented in the schema. The description adds no additional parameter semantics beyond referencing how jobs are started. Baseline of 3 is appropriate since the schema carries the semantic weight.

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: getting the status or result of a job started by specific tools. It distinguishes itself from the sibling tools (which are app-related) by focusing on long-running job polling. The verb 'get' and resource 'job status/result' are specific and unambiguous.

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: for jobs started by deep_research, translate_pdf, or make_slides. It also gives concrete polling instructions (every 15-30 seconds until done/error) and how to handle pending vs. complete states. This is clear operational guidance beyond merely saying 'use this to check jobs'.

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, idempotentHint=true, and destructiveHint=false. The description goes beyond annotations by specifying the informational content returned (use instructions, benchmark scores, repository, URL), which helps an agent anticipate the response shape and utility. It doesn't contradict any annotation.

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 that conveys the tool's purpose and enumerates specific content types without any filler. Every phrase earns its place, making it highly scannable for an agent.

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 one parameter, a rich output schema (indicated by has_output_schema=true), and strong annotations, the description sufficiently explains what the tool does and what it returns. No significant contextual gaps remain.

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% with the slug parameter described as 'Application slug, from list_apps.' The tool description adds no additional parameter details beyond the schema, so the baseline 3 for high schema coverage 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?

The description begins with 'Full details of one hosted application', which is a specific verb+resource formulation. It further enumerates the exact detail types (what it does, how to use, benchmarks, source repo, URL), clearly distinguishing it from sibling tools like list_apps or build_app.

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 singular 'one hosted application' implies this is for retrieving a single app's details, while the schema's parameter description 'from list_apps' reinforces the typical workflow. However, the tool description itself doesn't explicitly mention alternatives or when not to use it, though the intent is clear from context.

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 read-only, idempotent, and non-destructive behavior. The description adds valuable context that these apps normally require local setup but are pre-configured here, which informs the agent about the execution environment. It does not describe return format, but output schema exists, so this is acceptable.

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 yet information-dense: it states purpose, adds environmental context, gives task examples, and ends with explicit exclusions. Every sentence contributes value, with no wasted 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 the tool's simplicity, one optional parameter, and the presence of annotations and output schema, the description is fully complete. It covers purpose, usage examples, and explicit alternatives, leaving no critical gaps for an agent to select and invoke 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?

Schema coverage is 100% (one parameter 'category' with its own description). The tool description does not mention the parameter, but the schema already fully explains it. Per rubric, baseline is 3 when schema covers parameters; the description adds no extra parameter semantics.

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 lists open-source AI applications hosted at AI NetCafé, with a specific verb ('List') and resource ('open-source AI applications'). It also distinguishes from sibling tools (build_app, check_job, get_app) by focusing on listing ready-to-run apps, and explicitly names other task-specific tools to call directly.

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

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

The description provides explicit guidance: 'Use this to find a tool for a task like...' with concrete examples, and directly states when NOT to use it: 'Do not call this first when the request already clearly matches compare_models, translate_pdf, deep_research, or make_slides; call that task tool directly.' This gives clear when-to-use and when-not-to-use context.

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