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

The description adds significant behavioral detail beyond the annotations: it reveals that the build is asynchronous ('Returns a job_id immediately — poll with job.status until status='completed'), explains the response includes a dataset_id, and describes the required workflow. Annotations only indicate non-readonly and non-destructive, but the description enriches this with async nature and polling instructions.

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 (around 10 lines) and well-structured: a one-sentence summary, followed by behavioral notes, then an Args section. Every sentence provides essential information. The structure is front-loaded with the core purpose and step number, making it easy to scan.

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 necessary aspects for a tool in a workflow: prerequisites (completed execution), side effects (async build, dataset created), return value (job_id), and next steps (poll and then export). Given the presence of an output schema, the description does not need to detail return format. It provides a complete context for correct usage.

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 0% schema description coverage, the description fully compensates by providing detailed semantics for all parameters: execution_id is from a completed data_process job, name is auto-generated from filename if omitted, description is optional. This adds crucial context absent from the schema, making parameter usage clear.

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: 'Package extracted records into a dataset for export (Step 4)'. It specifies the action (build), the resource (dataset), and its role in a multi-step workflow. It distinguishes itself from sibling tools like dataset.export and job.status by explaining that this step is required before export and that the returned job_id must be polled.

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: 'Triggers an async dataset build from a completed execution.' It states the prerequisite (completed execution) and the subsequent step ('This step is required before calling dataset.export'). It also tells the user to poll job.status until complete, offering a clear usage pattern. No alternative tools needed for this specific step.

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?

Adds substantial context beyond the annotations: returns paginated chunks with fields (text, token count, metadata including quality grade, PII masking status, document type, language), explains the min_quality threshold behavior, and notes the indexing prerequisite. This complements the readOnlyHint and idempotentHint annotations without contradiction.

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 well-organized: a concise summary sentence followed by return details and a structured Args list. Every sentence adds value, and the length is appropriate given the 5 parameters.

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 the tool's purpose, prerequisites, parameter semantics, return content, and pagination guidance. With annotations and an output schema present, this is fully actionable for an agent to select and invoke the 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 0% schema description coverage, the description fully compensates by documenting every parameter in the Args section, including defaults, allowed values, and an example for min_quality. This provides meaning far beyond the raw schema properties.

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: 'Retrieve LangChain/LlamaIndex-ready text chunks from an indexed dataset.' This specific verb+resource+scope distinguishes it from siblings like dataset.search and dataset.export.

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?

Provides clear context: Pro+ plan restriction, the prerequisite that the dataset must be indexed via dataset.index(), and guidance to use FlexOrchRetriever/Reader for automatic pagination. However, it does not explicitly mention when not to use this tool or directly contrast with sibling tools.

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 (safe read). Description adds key behavioral details: returns content as UTF-8 string directly, no file download, and binary format limitations. No contradictions.

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?

Efficient single paragraph that front-loads core purpose, then logically covers response format, prerequisites, format guide, and limitations. Every sentence adds value with no redundancy.

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 tool complexity and existing output schema, description fully covers prerequisites, parameter usage, format options, and limitations. No missing information 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?

Despite 0% schema description coverage, description thoroughly explains both parameters: format (lists each format's use case) and dataset_id (source from completed build). Go beyond schema defaults and types.

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's purpose: 'Download all records from a built dataset as text (Step 5 — final step).' It distinctively identifies itself as the retrieval step after building, distinguishing from sibling tools like dataset.build and job.status.

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 provides prerequisites: call get_job_status after build_dataset, wait for status='completed', and use dataset_id from that response. Also advises when not to use (binary formats) and directs to dashboard alternative.

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 idempotentHint annotation, the description reveals async behavior, internal steps (splitting, embedding, storing), typical completion time (10–60 seconds), and the effect of re-indexing with fresh embeddings. This adds substantial context not captured in 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 front-loaded with a one-sentence summary, followed by concise behavioral details and a clear Args section. Every sentence adds value, and the structure is easy to scan.

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, an output schema, and a clear description of the operation, the tool is fully specified. It covers prerequisites, async nature, idempotency, and the relationship to sibling tools.

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 specifies an integer dataset_id, but the description adds the source and meaning: 'ID of the built dataset to index (from job.status after dataset.build).' This provides exactly the necessary context for the parameter.

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 explicitly states the verb 'Trigger semantic indexing' and the resource 'dataset', distinguishing it from siblings like dataset.build and dataset.chunks. It also notes it is required before using dataset.chunks, which clarifies its role.

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 states when to use: 'required before using dataset.chunks (Pro+ plan)' and the post-condition 'After indexing, use dataset.chunks(dataset_id).' It also references the prerequisite from job.status after dataset.build, giving a clear workflow.

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 readOnlyHint=true and idempotentHint=true, so safety is clear. The description adds behavioral context like requiring an existing dataset, plan-based mode restrictions, and a clear upgrade message for insufficient plans. This enriches transparency beyond 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 well-structured with a front-loaded purpose sentence and an organized Args block. It is informative without unnecessary verbosity, though slight tightening could improve 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 complexity (6 params, plan restrictions, and preconditions) and the presence of an output schema, the description covers all essential aspects: purpose, usage guidance, parameter details, plan dependencies, and return value expectations.

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?

Despite 0% schema description coverage, the Description's Args block thoroughly explains each parameter, including defaults, max values, options, and plan dependencies for mode. This fully compensates for the schema's lack of 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 'Search across all indexed FlexOrch datasets by keyword or meaning.' It uses a specific verb (Search) and resource (datasets), and distinguishes from sibling tools like dataset.build or document.process.

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 advises when to use ('to find specific documents or records without processing a new file') and mentions prerequisites ('Requires at least one dataset to exist'). It also details plan restrictions for modes, though lacks explicit 'when not to use' beyond plan limitations.

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?

Discloses asynchronous processing, immediate return with job_id, and the need for polling. Annotations (readOnlyHint=false, destructiveHint=false) are consistent; the description adds critical behavioral context beyond 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?

Well-structured with clear sections and bullet points for args, but slightly verbose. Could be tightened without losing clarity, but still 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?

Covers all necessary context: tool purpose, async flow, polling instructions, prerequisites, and supported formats. With an output schema present, lack of return description is 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?

Despite 0% schema coverage, the description fully explains each parameter: file_url (public URL, max 50MB, formats), mask_pii (masking behavior, default true), document_type (optional hint, list of values). This compensates completely.

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 'Submit a document for processing — this is always the first step (Step 1 of 5).' It details the pipeline (download, FlexOrch classification, extraction, PII masking, quality scoring) and distinguishes itself from sibling tools like job.status and job.result.

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?

Explicit guidance to use as the first step and instructs the agent to call job.status every 3-5 seconds then job.result. It also lists supported file types and constraints, leaving no ambiguity about when this tool is appropriate.

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 readOnly and idempotent hints, and the description adds critical behavioral context: masked fields appear as [MASKED_TYPE] placeholders and raw PII is never returned. It also discloses the conditional fields_hint field, giving the agent a clearer picture of what to expect in the response.

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 moderately long but well-organized with notes and an Args section. It front-loads the main purpose and every sentence provides value. Minor redundancy exists between 'completed document' and 'completed data_process job', but the overall structure is clear and navigable.

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 provides strong pipeline context, including when the tool is applicable, what the fields_hint implies, and how to proceed to file export. It also covers security relevant to PII. Given that an output schema exists, the high-level summary of returned fields is a useful addition rather than a necessity, making the description complete for tool selection and 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?

The schema only lists execution_id as an integer without explanation (0% description coverage). The description compensates by explaining that execution_id comes from a completed data_process job's job.status response and clarifies that dataset_build jobs use dataset_id instead. This adds meaningful semantic context and prevents parameter misuse.

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 ('Read') and resource ('structured fields extracted from a completed document'), clearly stating what the tool does. It distinguishes itself from sibling tools by positioning it as 'Step 3' in the pipeline and referencing related steps (dataset.build, dataset.export) and the job.status source.

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 the tool: after a completed data_process job, using the execution_id from job.status. It provides alternatives and next steps via the fields_hint to call dataset.build, and for file retrieval, dataset.build → dataset.export. It also warns against using dataset_build IDs, preventing common mistakes.

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 mark the operation as read-only and idempotent. The description adds valuable behavioral details: polling interval, expected terminal statuses, and job-type-specific response fields (execution_id vs dataset_id), which goes beyond what annotations provide.

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 well-structured with a clear intro, polling instructions, job-type-specific guidance, and an Args section. Every sentence provides actionable information with no redundancy, keeping it appropriately 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?

Given the tool's role in a multi-step workflow, the description covers when to call, how to poll, what to expect in the response, and which sibling tools to invoke next. With an output schema present, full return-enumeration is unnecessary; this description 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 input schema has no description for job_id, but the description explains job_id is 'Job ID returned by document.process or dataset.build', giving clear origin and purpose. This fully compensates for the 0% schema coverage.

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: polling a job until it finishes, and explicitly ties its use to after document.process or dataset.build. It also distinguishes from job.result by explaining the next step for different job types.

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?

Provides explicit usage guidance: call after document.process or dataset.build, poll every 3–5 seconds until completed/failed, and pass the appropriate ID to job.result or dataset.export. This directly instructs when to use and what to do next.

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