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 goes further by disclosing that it merges four API calls and that missing parts are returned as null instead of failing the whole request. This adds meaningful behavioral context beyond 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 well-structured with a purpose statement, rationale, Args, and Returns sections. It is slightly longer than necessary but each sentence serves a purpose, and the key information is front-loaded in the first sentence.

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, why it exists, parameter semantics, return format, and partial-failure behavior. With supportive annotations and a clear output schema, it is fully sufficient 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?

The input schema already provides rich descriptions for both parameters (e.g., include_sample says 'Include ~10 sample rows. Set to false if the dataset has very wide columns.'). The description's Args section merely restates the schema without adding new meaning, so it does not elevate above the baseline.

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 'Returns everything needed to configure a training run over a dataset,' clearly stating the specific verb (returns) and resource (dataset). It also explains that it aggregates four raw API endpoints, which distinguishes it from sibling tools like dashai_list_datasets and dashai_train_model.

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 conveys when to use this tool: when deciding which columns are inputs and outputs for training requires seeing them together. It gives clear context but does not explicitly name alternatives or state when-not-to-use conditions, falling slightly 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?

The description reveals meaningful internal behavior beyond the annotations: it reads a SQL row, aggregates an Arrow dataset stored on disk, strips paths/row lists, and ensures the label list never leaves the function. This is strong behavioral disclosure that aligns with readOnlyHint and idempotentHint.

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 main purpose, then uses compact context about the underlying GET /predict/ row and the returned JSON shape. Every sentence contributes useful information, though the Arrow/GET explanation could be slightly tighter.

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 single-parameter read-only tool with clear annotations, the description covers what the tool does, what it receives, what it returns, and what it deliberately strips away. It even includes the exact JSON shape, and it leaves no major ambiguity for selecting or invoking it.

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, prediction_id, is already described in the schema as 'Id returned by dashai_predict'; the description essentially repeats that without adding new constraints, examples, or edge-case guidance. The schema does the heavy lifting, so this is acceptable but not enriched.

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 sharp statement: 'Returns class counts for a finished prediction — never the rows.' This clearly identifies the resource, the action, and the exact scope, distinguishing it from row-level or run-level 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 description explicitly states that it applies to a finished prediction and that the prediction_id comes from dashai_predict. It also implies that this tool is not for retrieving raw rows, since 'paths and row lists are stripped.' It does not name sibling alternatives directly, but the usage context 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?

Despite annotations already declaring readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, the description adds important behavioral context: metrics are empty for unfinished runs (not an error) and the return format (JSON with model parameters, status, and per-split metrics). This enhances transparency beyond 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 concise and well-structured: a one-sentence purpose, followed by a use-case note, and clearly labeled Args/Returns sections. Every sentence adds value, and the format 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?

For a simple read-only tool with one parameter and an output schema, the description fully covers the relevant context: the return value's structure, the dependency on run completion, and the absence of errors for empty metrics. No significant gaps are present.

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 0%, so description must compensate. It explains the nested 'params' structure containing run_id and describes run_id as the run identifier. While it repeats the schema's 'run id' description, it clarifies the nesting and provides enough context for a single-param tool. It could add how to obtain run_id (e.g., from list_runs), but it's sufficient.

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 action and resource: 'Returns the configuration and metrics of a training run.' It clearly differentiates from siblings like dashai_job_status (status only) and dashai_list_runs (list only) by focusing on full run details. The tool's role is 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?

Explicit guidance is provided: 'This is where results are read once dashai_job_status says `finished`.' This instructs when to use it and implies the alternative workflow with job_status, while also warning that incomplete runs yield empty metrics. This is clear usage direction.

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, idempotent, and non-destructive behavior, so the bar is lower. The description adds meaningful context by explaining the status values (not_started, started, finished, error) and their practical interpretation, which helps the agent decide whether to keep polling.

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 compact and well-structured: a clear purpose line, a brief but valuable status explanation, then Args and Returns sections. Every sentence adds necessary information with no filler or repetition.

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?

This is a simple polling tool, and the description covers purpose, parameter source, return format, and status interpretation. With annotations providing the safety profile, there is no critical missing context.

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 schema_description_coverage is reported as 0%, the description explicitly documents the 'job_id' parameter and clarifies that it is returned when enqueuing. The schema also includes a similar description, so the parameter's meaning is fully covered and not just left to schema alone.

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 'Polls the status of an enqueued job', using a specific verb and resource. It also lists examples (training, prediction, explanation), which distinguishes it from sibling tools like dashai_train_model or dashai_predict.

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 clear context on when polling is useful, explicitly stating that a 'started' status is worth waiting on while 'error' will not improve with further polling. This gives implicit when-to-use and when-not-to-use guidance, though it does not explicitly name alternative 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, openWorldHint, idempotentHint, and destructiveHint=false. The description adds behavioral context beyond those: the catalogue is plugin-dependent, names cannot be guessed, and an unfiltered call returns a long result. It also documents the return JSON structure, including the 'schema' field, which is not present 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 well-structured: a one-sentence purpose, a high-value usage note, and compact Args/Returns sections. It is not overly long and every sentence carries useful information, though the Args section partly repeats schema content.

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, the description covers purpose, when to use it, the parameter, the return format, and a critical behavioral caveat (plugin-dependent catalogue). It is complete for an agent to invoke the tool correctly without additional context.

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, 'params', is described in an Args section, and the 'types' filter's valid values are listed. While the input schema's description for 'types' already provides the same valid values and the long-output caveat, the tool description nonetheless clarifies the structure of the 'params' wrapper and the meaning of the returned 'schema' field, adding value beyond the raw schema.

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 'Lists the registered components: models, metrics, tasks and optimizers', using a specific verb and enumerating the resource types. This clearly distinguishes the tool from sibling tools like dashai_list_datasets and dashai_describe_dataset.

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 'ALWAYS use this before dashai_train_model' and explains that names are exact/case-sensitive and the catalogue changes with installed plugins. This provides strong when-to-use guidance and a rationale for why the tool must be called first, which is more than typical.

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 provide readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to restate these. It adds value by detailing the exact return fields (id, name, date, status) and the empty response behavior, which are not evident from annotations alone.

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 summary, sections for args and returns, and a bullet-point parameter explanation. Every sentence adds value and there is no redundant fluff.

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 description covers the purpose, usage, return format, and empty-case behavior. It also references a sibling tool for deeper inspection, making the description fully self-contained 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?

The description explains the 'limit' parameter with its range (1-200) and default (50), which compensates for the low schema description coverage (0% as per context). It provides enough detail for an agent to use the parameter correctly without relying solely on the schema.

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 ('Lists') and a clear resource ('datasets loaded in dashAI'). It clearly distinguishes from sibling tools like dashai_describe_dataset by specifying it returns only summary fields, making it easy for an agent to choose this tool for overview purposes.

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 states when to use this tool ('just enough to pick one') and directs the user to dashai_describe_dataset for detailed column information. It also explains the behavior when no datasets exist, giving clear context for expected use cases.

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, so the safety profile is well covered. The description adds return format and filtering context, but does not disclose additional behavioral traits such as rate limits or auth needs. This is acceptable given the strong annotations, but not exemplary.

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 compact and well-organized: a clear purpose statement, a usage hint, a structured Args section, and a Returns section. Every sentence adds value, and the most important information (what it does) is front-loaded.

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 straightforward list tool, the description covers purpose, usage context, parameters, and return shape. It is complete enough for an agent to select and invoke the tool without needing external documentation, especially with strong annotations and a simple schema.

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 context showing 0% schema description coverage, the description explicitly explains both parameters: model_session_id as 'filter by experiment' and limit as 'maximum to return, 1-200 (default 50)'. This fully compensates for the schema gap and adds practical meaning beyond parameter names.

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 'Lists the recorded training runs, with their status,' which clearly states the action (list) and resource (training runs). It also distinguishes from siblings by focusing on training runs and comparing models within an experiment, avoiding confusion with list_datasets or get_run.

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 phrase 'Useful for comparing models trained within the same experiment' provides a clear context for when to use this tool. It implies usage for browsing runs and filtering by experiment, but does not explicitly exclude alternatives like get_run for single-run details, so it misses the top score.

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 annotations by explaining that the tool creates a Prediction row and then enqueues a PredictJob, that the job expects prediction_id rather than run_id, that passing only run_id causes a KeyError, and that the operation is asynchronous. This is valuable behavioral disclosure beyond the readOnlyHint/idempotentHint flags.

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: a one-sentence purpose, a clear async follow-up note, a concise two-step internal flow, a warning about a specific failure mode, and an Args/Returns recap. Every section adds important operational knowledge without padding.

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 of the two-step internal flow, the description covers the operation end-to-end: input semantics, async behavior, response shape, and follow-up tool. The KeyError warning is especially valuable for correct use of the returned prediction_id.

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 includes an Args section explaining run_id as a finished run and dataset_id as optional with a default to the run's training dataset. It adds important context about the internal run_id/prediction_id distinction, though the input schema already provides detailed descriptions for the nested 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?

The description opens with a specific verb and resource: 'Enqueues a prediction using the model of an already finished run.' It clearly distinguishes this from training, dataset listing, and job-status tools, and it states that the operation is asynchronous and returns a job_id.

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 clear usage context: use it for a finished run, the operation is asynchronous like training, and the result should be followed via dashai_job_status. It does not explicitly enumerate when not to use it, but it provides enough contextual guidance 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?

The description goes beyond the readOnly/idempotent annotations by detailing the exact response shape, including reachability, queue state, dataset/run counts, and API compatibility status. It also discloses the failure string format ('Error: <what happened and what to do>'), so the agent knows what to expect on both success and failure.

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 purpose, followed by a concise use-case directive and then well-structured Args/Returns sections. The return schema is detailed but necessary because it documents a complex JSON payload, so every section earns its place.

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 read-only health-check tool, the description is complete: it explains when to call it, what it checks, what the output contains, what the compatibility field means, and what failure messages look like. The rich output schema and annotations cover the remaining structured details.

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 takes no meaningful parameters: the input schema defines a NoArgs object and the description explicitly states 'no parameters.' With effectively zero parameters, the baseline is 4, and the description's confirmation removes any 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 opens with a specific verb and resource: 'Checks that dashAI is running and summarizes what is loaded.' It also distinguishes this tool from sibling data-operations tools by framing it as the backend health diagnostic, and explicitly separates 'dashAI is down' from 'that id does not exist'.

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?

Usage guidance is explicit and actionable: 'Call this FIRST when something fails or when you do not know whether the backend is up.' It also tells the agent what diagnostic distinction the tool provides, which directly informs decision-making about which problem is being debugged.

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 provide readOnlyHint=false, destructiveHint=false, idempotentHint=false, but the description adds critical behavioral context: it enqueues a job and returns immediately, does not wait, training can take minutes/hours, and it collapses three raw API calls. Error behavior is also described ('On failure: "Error: ..." stating which parameter dashAI rejected'). This goes well beyond annotation 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?

The description is structured with clear paragraphs: function, async behavior, API collapsation, Args, Returns, Examples. Every sentence adds value, but the Args section largely duplicates schema information and makes the description longer than strictly necessary. Still, it is front-loaded with the most important usage rules and alternative references.

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 complexity (async, multi-step training, many parameters, output schema), the description covers all necessary context: how it works, how to poll, what returns, error handling, and how it differs from siblings. It even provides usage examples. No significant gap remains.

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 already has detailed descriptions for nested TrainModel properties. The description's Args section condenses these into a readable list and adds context by explaining that the parameters map to the three API calls (session, run, job). It also notes 'proportions adding up to 1.0' for splits, reinforcing the schema. This adds semantic clarity beyond the raw schema, especially given the top-level schema coverage is 0%.

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 opens with 'Trains a model on a dataset and returns the id of the enqueued job.' This is a specific verb+resource statement that clearly distinguishes the tool from siblings like dashai_get_run ('Do not use it to read results') and dashai_job_status (polling). It also details the collapsed API calls, leaving no ambiguity about what the tool accomplishes.

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 when to use: 'It does NOT wait for it to finish... progress is polled with dashai_job_status.' Provides a clear exclusion: 'Do not use it to read results: that is dashai_get_run, with the run_id.' This gives direct when/when-not guidance relative to siblings.

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