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

With no annotations provided, the description carries the full burden. It discloses that it does not run and that tool commands come from operator config, but it does not explain side effects like file creation, permissions, reversibility, or what the return value looks like. This is minimal transparency for a tool that likely writes configuration files.

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 three short sentences, front-loaded with the main action 'Prepare input files.' It is concise and does not waste words, though the final clause about 'Native batch folder, not an SWB project' adds context without being verbose.

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 four required parameters including nested objects and no output schema, the description is incomplete. It does not explain the required format for files and stages, the meaning of run_id and project, or what happens after execution. It also lacks guidance on when to use it versus siblings, making it insufficient for an agent to call correctly without additional knowledge.

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 0%, so the description must compensate. It only hints that stages contain tool and input_file, but it does not explain project, run_id, or the structure of files. The description adds almost no meaning to the parameters beyond what the schema already shows, leaving most parameter semantics undocumented.

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 'Prepare input files' and explains that stages specify tool and input_file, which clarifies the creation/configuration nature. It also distinguishes itself from running tools by explicitly stating 'Does not run.' However, the description does not explicitly say it creates an experiment record, which might be ambiguous given the tool name, but it is clear enough for a setup step.

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 implies usage context: it prepares input files and does not run, so it is used before submit_experiment. It also mentions 'Native batch folder, not an SWB project,' which hints at environment suitability. However, it does not explicitly name alternative tools or provide when-not-to-use conditions, leaving some inference required.

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 must carry the full burden of behavioral disclosure. It only states what data is read, but does not mention side effects (though 'Read' implies non-mutating), authentication requirements, error behavior if run_id is invalid, or any constraints. It is minimal and does not disclose potential limitations or security considerations.

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, clear sentence that front-loads the action ('Read') and lists the specific data items. There is no fluff or redundancy; every word 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?

Given the low complexity (one parameter, no output schema), the description partially covers what is returned (execution state, process IDs, timing, manifest, validation label) but omits critical context such as whether it returns a single object or list, error handling, and any required permissions. It is not fully complete for an agent to call it confidently.

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 description coverage is 0% for the single parameter run_id, and the description does not mention it at all. The parameter name is self-explanatory as a run identifier, but the description adds no meaning beyond the schema, failing to compensate for the lack of schema documentation.

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 the verb 'Read' and specifies the resource (execution state, process IDs, timing, manifest, validation label). It clearly indicates this is a retrieval operation for experiment details, and the tool name 'get_experiment' reinforces that. It distinguishes from siblings like 'list_experiments' (which likely returns a list) and 'read_log' (which reads logs), though it does not explicitly name alternatives.

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 its siblings. It does not mention alternatives, conditions for selection, or exclusions. An agent cannot determine from the description whether to call this instead of list_experiments or read_log.

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, the description carries the burden of behavioral disclosure. It usefully reveals that large TDR files are not read into model context, suggesting a low-cost listing operation. However, it does not clarify return behavior, side effects, or whether the index is up-to-date.

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 one concise sentence, front-loads the purpose, and adds a useful caveat without 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?

For a one-parameter listing tool, the description covers the central caveat but leaves gaps: what exactly is returned, how 'run_id' scopes the artifacts, and what 'native files' means. There is no output schema to compensate, so the agent has to infer part of the contract.

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 0% and the description never mentions 'run_id' or how it relates to the native files being indexed. The parameter is somewhat self-explanatory from its name, but the description adds no meaning beyond 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 states a specific action ('Index') on a resource ('native files') and adds a distinguishing behavioral note about not reading large TDR files into model context. It doesn't explicitly name sibling tools, but the second clause helps separate it from content-loading operations.

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 'does not read large TDR files into model context' implies this tool is appropriate when you want to index/listing without loading large content, but it does not explicitly say when to prefer it over alternatives such as read_log or list_experiments.

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 full burden of behavioral disclosure. It explicitly states 'Read-only,' which is a meaningful safety-related behavior, and mentions pagination. However, it does not disclose ordering, whether results include all experiment states, or what happens when pagination boundaries are exceeded. Still, the core behavioral trait is covered.

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 short sentences with no filler. 'List persistent experiments' states the core action, 'paginated' covers the parameters, and 'Read-only' covers safety. Every word earns its place and the most important information 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 simple list operation with two optional, well-understood pagination parameters and no output schema, the description is nearly complete. It tells the agent what the tool does, that it is read-only, and that it supports pagination. Additional details like result ordering or default page size would be nice, but they are not essential 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?

Schema description coverage is 0%, so the description must compensate. It does not explain limit or offset individually, but the word 'paginated' conveys how these parameters function together. Since the parameters are simple integers with defaults and self-explanatory titles, the minimal description provides sufficient semantics without much additional detail.

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 verb and resource: 'List persistent experiments.' It also signals pagination and read-only behavior, which clearly distinguishes it from siblings like get_experiment, create_experiment, and submit_experiment. The name alone would be somewhat generic, but the description adds enough specificity to make the tool's purpose 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 implies use when listing experiments in a paginated, read-only fashion, but it does not explicitly name alternatives or state when not to use this tool. The read-only hint contrasts with create_experiment and submit_experiment, and 'list' contrasts with get_experiment, but these contrasts are left for the agent to infer rather than explicitly guided.

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 exist, so the description carries the full burden. It discloses that reads are bounded and that offset is byte-based, which is useful context. However, it does not mention error behavior, response format, rate limits, or what 'bounded' means in size.

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 terse sentence with no filler. Every word contributes, and it front-loads the core action and key scoping detail.

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 four parameters, no annotations, and no output schema, the description is far too sparse. It does not explain the run_id parameter, the meaning of limit, pagination beyond byte offsets, or what the caller should expect in the result.

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 0%, so the description must compensate for all parameters. It only clarifies the semantics of 'offset' (bytes), leaving run_id, limit, and stage_index unexplained in both schema and description. That is weak compensation for a four-parameter tool.

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 verb ('read') and resource ('log increments'), and the byte-offset detail helps characterize the operation. It is clearly distinct from sibling tools about experiments and artifacts, though 'increments' is slightly vague and the description does not mention the run_id context.

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?

There is no explicit guidance on when to use this tool versus alternatives. The intended use is implied by the name and description, and the siblings are unrelated, so confusion is unlikely, but no exclusions or alternative routing are provided.

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, the description carries the full burden and delivers meaningful behavioral detail: the launch is asynchronous, duplicate requests do not restart the experiment, and there is no fixed runtime kill. This goes beyond the tool name and schema, though it does not cover response shape, error behavior, or auth requirements.

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?

Three short sentences, each adding distinct value: the main action, duplicate-request idempotency, and polling/no-kill expectations. No filler or redundancy, and the core action 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?

The description is adequate for a one-parameter submission action, but with no output schema and no annotations, it omits how the agent should determine submission success and which specific sibling to poll for status. 'Poll status' is helpful but vague about the mechanism.

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 provides only a run_id string with no description, and the description does not explicitly define run_id. It weakly ties run_id to 'a prepared experiment' and duplicate-request behavior, but the semantic burden falls mostly on the parameter name itself.

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 verb and resource: 'Launch a prepared experiment asynchronously.' It clearly distinguishes this from sibling tools like create_experiment (preparation) and get_experiment/read_log (monitoring), so an agent can tell what action it performs.

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 implies when to use the tool—on an already-prepared experiment—and gives follow-up guidance to 'Poll status.' However, it does not explicitly name alternatives or say when not to use this tool versus create_experiment or get_experiment, so the guidance is mostly implicit.

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