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

No annotations are provided, so the description must carry full behavioral disclosure. It only says 'cancel' or 'mark for cancellation' without detailing side effects, whether cancellation is immediate, or what happens to the task state. This lacks depth for a mutation tool.

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 sentence that is front-loaded with the action and covers both queued and running scenarios. No extraneous 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 presence of an output schema and high schema coverage, the description is adequate but minimal. It could mention prerequisites (e.g., task must exist) or error states, but the current text suffices for basic understanding.

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%, so the schema already describes all parameters. The description adds minimal value by linking task_id to origin_bridge_submit_task, but does not enhance understanding of host, port, token, or timeout 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 clearly states the tool cancels or marks for cancellation an Origin bridge task, using specific verbs 'Cancel' and 'mark'. It distinguishes from sibling tools like origin_bridge_submit_task and origin_bridge_task_status by focusing on cancellation.

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 distinguishes between queued and running tasks, providing some context. However, it does not explicitly state when to use this tool versus alternatives (e.g., checking status first via origin_bridge_task_status) or any exclusions.

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 provided; description only states it lists recent tasks. Does not disclose side effects, authentication requirements, or pagination behavior. Returns an output schema, but behavioral details are minimal.

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?

A single sentence that is concise and front-loaded with the action and resource. 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?

For a simple list tool with full schema coverage and an output schema, the description is complete enough. It provides the necessary context for an agent to understand its purpose.

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 parameters are well-documented in the schema. The tool description adds no additional meaning beyond stating the list operation.

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 recent Origin bridge background tasks, which is specific and distinguishes it from sibling tools like cancel, submit, and 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?

No guidance on when to use this tool versus alternatives (e.g., origin_bridge_task_status for a single task, origin_bridge_submit_task to create). Lacks usage 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?

With no annotations provided, the description carries the burden of disclosing behavioral traits. It accurately describes that the tool releases the automation connection by default and can force-close Origin when close_origin=True. This covers the key behavioral aspects, though it omits details about error handling or other 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 extremely concise, consisting of two sentences with no superfluous information. It front-loads the main action and provides additional detail in the second sentence, 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?

Given the tool has 6 parameters (all optional) and an output schema, the description adequately covers the essential behavior and the key parameter (close_origin). It does not explain return values, but the output schema likely handles that. The description is complete enough for an agent to understand the tool's core functionality.

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 100% coverage, so the baseline is 3. The description adds some context beyond the schema by explaining the default behavior for close_origin and the release action, but it does not substantially enrich the parameter meanings beyond what the schema already provides.

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: to ask the Origin GUI bridge to stop serving requests. It uses specific verbs ('stop serving') and distinguishes itself from sibling tools like origin_bridge_submit_task or origin_bridge_list_tasks, which are clearly different 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 description explains the default behavior and how to force-close Origin via close_origin=True, but it does not explicitly state when to use this tool instead of alternatives, nor does it provide exclusions or prerequisites. Usage guidance is implied but not comprehensive.

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 full burden for behavioral disclosure. It only hints at asynchronous execution ('queued background task') but does not disclose side effects, authentication requirements, error handling, or whether it is destructive. This is insufficient for a task submission tool.

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 with no wasted words. It efficiently conveys the core action, though it could benefit from slightly more structure (e.g., front-loading key constraints).

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?

Despite output schema existing, the description lacks important context: valid methods, task lifecycle, error handling, and how to retrieve results. Given the complexity (6 parameters, no annotations), more complete context is needed for effective use.

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?

Input schema has 100% coverage with adequate parameter descriptions. The tool description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.

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 action ('submit') and resource ('supported Origin bridge method') and indicates the result is a 'queued background task', distinguishing it from sibling tools like cancel or list tasks. However, it could be more explicit about the nature of 'Origin bridge' and the queuing behavior.

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?

No guidance is provided on when to use this tool versus alternatives (e.g., submitting directly). There are no prerequisites, error conditions, or mentions of other bridge task management tools among the listed siblings.

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 provided, so description carries full burden. It states 'Read' suggesting non-destructive behavior, but does not disclose potential behaviors like error handling, blocking nature, or prerequisites. The description is too brief to convey behavioral traits beyond the basic read action.

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?

Single sentence, no wasted words. The key information is front-loaded. Every word serves a purpose.

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 8 parameters and an output schema, the description is minimal. It does not explain parameter interdependencies (e.g., log_limit effect when include_logs is false) or scenarios. However, the presence of an output schema reduces the need to describe return values, keeping the score at a mid level.

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%, so baseline 3. The description does not add new meaning beyond what the schema already provides for each parameter. It mentions 'status, result, or optional recent logs' which aligns with include_result and include_logs, but the schema covers those details.

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 the specific verb 'Read' and clearly identifies the resource as 'status, result, or optional recent logs for an Origin bridge background task'. It effectively distinguishes from sibling tools like origin_bridge_cancel_task and origin_bridge_list_tasks.

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?

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., after submitting a task) or when not to use it. The description implies checking task status but lacks comparative 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?

No annotations are provided, so the description carries the full burden. It indicates read-only behavior ('List' and 'browse') but does not disclose edge cases (e.g., invalid path) or failure modes. Acceptable for a listing tool but lacks depth.

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 10-word sentence that immediately conveys the purpose without wasted words. It is front-loaded with the primary action and succinctly covers both listing and browsing modes.

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 high schema coverage and the presence of an output schema, the description sufficiently explains the tool's core functionality. It could mention result format or pagination, but the output schema likely covers that. Minor omission but not critical.

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 100%, with each parameter having a descriptive comment. The tool description adds context about slash-delimited paths, but the schema already explains the 'topic' parameter similarly. Baseline 3 is appropriate as the description adds marginal value over 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 clearly states the tool lists knowledge collections or browses a collection by slash-delimited path. It uses a specific verb ('List' and 'browse') and resource ('knowledge collections'), and implicitly distinguishes from sibling tools like origin_query_knowledge which queries content.

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: omit collection to list collections, provide collection to browse. However, it does not explicitly state when not to use the tool or mention alternatives among siblings, leaving some ambiguity for complex scenarios.

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 must bear the full burden of behavioral disclosure. It discloses that setting 'show' changes Origin visibility, implying a side effect beyond reporting. However, it omits details about read-only nature, output format, or other potential impacts, leaving significant gaps.

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 of 12 words. Every word contributes meaning, with no redundancy or fluff. It efficiently conveys the primary purpose and a key behavioral note.

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 presence of an output schema (not shown), return values are covered. The description covers the core purpose and one parameter effect, but lacks context about typical usage, relationship to siblings, and what 'runtime capabilities' entails. It is minimally adequate but not 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?

Schema coverage is 100% (both parameters described in schema), so baseline is 3. The description adds value for 'show' by explaining its effect on Origin visibility, but provides no extra context for 'refresh'. Overall, the addition is marginal but positive.

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 reports runtime capabilities, with a specific verb ('report') and resource ('runtime capabilities'). It also notes a secondary effect of the 'show' parameter. While it doesn't explicitly differentiate from sibling tools, the unique purpose is implied by the name and 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?

The description provides no guidance on when to use this tool vs. alternatives. There is no mention of prerequisites, typical use cases, or conditions under which this tool is preferred over sibling tools like 'origin_ping' or 'origin_query_knowledge'.

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 fully discloses expected outputs: column stats, issue list with severities, and 'passed' flag. It details threshold behavior and issue triggers, though it could mention read-only nature explicitly.

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 front-loaded purpose statement. Every sentence adds information—no redundant or filler 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 output schema exists, the description adequately covers behavior and expected results. It could mention that the tool is read-only, but overall it is complete for a diagnostic 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%, so baseline 3. The description adds value by explaining high_missing_threshold range and the meaning of 'passed' false, going beyond the schema's basic parameter 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 the tool checks worksheet data quality before plotting or analysis, listing specific reports (dtype, missing, unique) and issue types. This distinguishes it from sibling tools like origin_read_worksheet and origin_plot.

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 says to use 'before plotting or analysis', providing clear context. However, it does not mention when not to use or list alternatives, though no sibling tool has similar purpose.

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 full burden for behavioral disclosure. It mentions diagnosing connectivity but does not specify whether the tool makes live requests (though ping_origin parameter hints at this), requires authentication, or is read-only. The behavioral traits are under-specified.

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, direct sentence of 8 words, front-loading the purpose with no extraneous detail. 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 6 optional parameters and an output schema, the description is quite minimal. It does not explain the output format or the optional behavior like ping_origin. While output schema reduces burden, the tool's overall diagnostic flow is not fully conveyed, leaving gaps for a complex 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%, with each parameter having a description. The tool description adds no additional meaning beyond listing the areas (configuration, status file, connectivity), which maps to parameters. Baseline 3 is appropriate as schema does the heavy lifting.

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 the specific verb 'Diagnose' and clearly identifies the resource as 'Origin bridge configuration, status file, and connectivity'. This distinguishes it from sibling tools like origin_ping (simple ping) and origin_bridge_* (task management), providing a clear scope.

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 diagnostic use through the name 'doctor' and the listed areas, but it does not explicitly state when to use this tool versus alternatives like origin_ping or other bridge tools. No guidance on prerequisites or exclusions is 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?

No annotations are provided, so the description carries the full burden. It mentions supported features and that unsupported ones are reported in the plan, but lacks details on side effects (e.g., project modification), blocking behavior, or error handling. For a complex tool, this is insufficient.

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 sentences, front-loaded with purpose, and avoids redundancy. It earns its place, though it could be slightly more informative without losing 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 of the input schema (nested objects, many options), the description is too sparse. It does not explain the tool's lifecycle, return values (though output schema exists), or how it integrates with other tools like origin_plan_figure_spec. More guidance would significantly improve usability.

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%, and the schema already describes both parameters adequately (spec as 'Declarative FigureSpec...', dry_run as validation without changes). The description adds minimal semantic value beyond what the schema provides, so baseline 3 is appropriate.

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 it executes a declarative FigureSpec, distinguishing it from planning tools like origin_plan_figure_spec. The verb 'execute' combined with the resource 'FigureSpec' is 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 implies use cases for generating figures from specs, but does not explicitly state when to use this tool over siblings like origin_plan_figure_spec or origin_export_graph. No when-not or alternative guidance is 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?

No annotations provided, so description bears full burden. It does not disclose behavioral details such as what happens if the file exists (handled by overwrite parameter but not described), how file format is determined, or the effect on the Origin graph. The mention of 'create a new page' for graph_name is in the schema but not in the description.

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?

Single sentence, front-loaded with key information. Very concise, though it could incorporate more usage guidance or behavioral context without losing brevity. 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?

Output schema exists, so return values are covered. The description lacks context on the export process, file format handling, and interaction with the active graph. Adequate for a simple tool but leaves some gaps.

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 each parameter having a description. The description does not add additional meaning beyond the schema; it merely restates the overall purpose. Baseline of 3 is appropriate.

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 action (Export), resource (Origin graph), and output format (image/PDF). It distinguishes from siblings like origin_view_graph (viewing) and origin_format_graph (formatting). The verb and resource are specific.

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 for exporting graphs to files but provides no explicit guidance on when to use this tool vs alternatives (e.g., origin_format_graph for in-memory formatting) or when not to use it. No exclusions or prerequisites mentioned.

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?

Without annotations, the description must disclose behavioral traits, but it only lists what can be set. It doesn't explain side effects (e.g., rescale behavior), whether it modifies in-place, or if the graph must be active. Minimal transparency.

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?

Single sentence, no wasted words. Could be slightly more structured but 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?

Complexity is moderate (6 params, output schema present), but description is minimal. No mention of return value, no guidance on when rescale is needed, and no explanation of formatting effects.

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%, so baseline is 3. The description adds a summary grouping of parameters but no new constraints or interdependencies beyond what schema provides.

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 it sets graph long name, axis labels, legend visibility, and optional rescale. It distinguishes from sibling tools like origin_export_graph or origin_plot by focusing on formatting an existing graph.

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?

No guidance on when to use this tool versus alternatives. No mention of prerequisites (e.g., graph must exist) or context like 'use after plotting'.

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?

There are no annotations, so the description carries full burden. It only states 'Inspect', implying read-only, but does not disclose potential creation of a new page when graph_name is omitted (as hinted in the parameter description). This omission reduces transparency.

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 sentence, directly stating the purpose without any extraneous words. It is optimally concise and 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?

Given the tool's simplicity (one optional parameter, output schema present), the description is adequate but misses contextual details like default behavior (active graph vs. new page) and what the output contains. The parameter description fills some gaps, but the tool description alone is not fully 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?

Schema description coverage is 100%, so baseline is 3. The tool description adds no further meaning beyond what the schema already provides 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 uses a specific verb ('Inspect') and identifies the resource ('graph page, its layers, axes, and plots'), clearly distinguishing it from siblings like origin_view_graph (view) and origin_export_graph (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?

No guidance is provided on when to use this tool versus alternatives (e.g., origin_view_graph for rendering, origin_browse_knowledge for knowledge queries). The description lacks context 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?

With no annotations, the description carries full burden for behavioral disclosure. It states the tool imports into a 'new' worksheet, yet parameters like book_name and sheet_name suggest existing workbooks/worksheets can be specified, creating ambiguity. No mention of side effects, file existence requirements, error handling, or performance implications.

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 front-loads the core action and object, with no extraneous words. It efficiently communicates the essential purpose.

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 (10 parameters, no annotations, but with an output schema), the description is insufficiently complete. It omits any mention of return values, error conditions, behavior when files or sheets don't exist, or the relationship between parameters like book_name and the 'new' worksheet claim.

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 covers all 10 parameters with descriptions (100% schema coverage), so the description adds no extra parameter-level meaning. Baseline 3 is appropriate; the description lists file types which partially reinforces the path parameter but does not deepen understanding of other parameters like encoding or na_values.

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: importing specific file formats (CSV, TSV, etc.) into a new Origin worksheet. It uses a specific verb ('Import') and resource ('Origin worksheet'), effectively distinguishing it from sibling tools like origin_read_worksheet or origin_write_worksheet.

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 for importing external data files into a new worksheet but provides no explicit guidance on when to use this tool versus alternatives, such as origin_read_worksheet for reading existing data or origin_write_worksheet for writing data. No when-not or alternative references are given.

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 provided, so description must cover behaviors. It mentions connecting and reporting status, but does not specify what status includes or side effects (e.g., making Origin visible via 'show' parameter). Adequate but not detailed.

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?

One efficient sentence with no wasted words, but could be slightly more informative without becoming 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?

Given the simple tool, full schema coverage, and existence of an output schema, the description is largely complete. Only missing details about the status report format.

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%, and the tool description does not add extra meaning beyond the schema's parameter description. Baseline of 3 is appropriate.

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 connects to Origin/OriginPro and reports basic status, which is a distinct purpose from sibling tools that perform specific operations like task management or plotting.

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?

No explicit guidance on when to use this tool versus alternatives, but the purpose is straightforward and implies use for connectivity checks before other operations.

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, and the description fails to disclose important behavioral traits: side effects (none, but not stated), resource requirements, or error handling. The word 'validate' implies read-only, but this is not explicit.

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 sentence, which is concise but may be too brief for a tool with a complex input schema. It earns its place but lacks structured detail like bullet points or sections.

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 FigureSpec and the absence of annotations, the description is incomplete. It does not explain the return format (planned operations), validation behavior, or potential errors. An output schema exists but its content is not leveraged.

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 baseline is 3. The description adds only generic phrasing ('Declarative FigureSpec describing data, layout, plots, style, export, and QA'), which adds minimal insight beyond the schema field 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 the tool validates a FigureSpec and returns planned Origin operations, distinguishing it from execution-oriented siblings like origin_execute_figure_spec. The verb 'validate' and noun 'FigureSpec' are specific.

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?

No guidance on when to use this tool versus alternatives (e.g., execute vs plan), no prerequisites or conditions for use. The description provides no when-to-use or when-not-to-use information.

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 behavioral disclosure burden. It adds useful detail about selected_cols interpretation (first column as X, remaining as Y, one-column as Y-only), but it does not discuss side effects such as whether a new graph page is created, whether existing pages are modified, or what the path must point to.

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 concise sentences that front-load the tool's purpose and then immediately address routing and selected_cols behavior. No filler or redundancy; every sentence 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 tool has 9 parameters and a 31-value enum, the description covers the core plot creation logic and selected_cols convention but leaves the required 'path' parameter unexplained ('see the tool description', yet the description never ties path to a table file). Other parameter interactions (style_mode, palette_name, export_path) are left entirely to schema definitions, which is acceptable but not comprehensive.

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%, so the baseline is 3. The description adds extra meaning to selected_cols, explaining the X/Y column mapping that the schema's 'include in the plot' does not. It also frames the kind enum as a compact-route selector, enriching the schema's simple 'kind' description.

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 ('Create a table-based plot selected by kind') and clearly distinguishes this generic entry point from dedicated origin_plot_* tools and origin_plot_matrix_id. It names the exact kind-based routing, making the tool's role 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 explicitly says matrix-range plots should use origin_plot_matrix_id, providing a clear when-not case, and mentions that dedicated origin_plot_* tools exist as alternatives for each route. However, it does not address when to prefer this over sibling origin_plot_auto, leaving some selection ambiguity.

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 behavioral disclosure. It does disclose the routing decision logic (intent vs. column types/cardinality/selected columns) and signals a side effect by saying it 'creates the plot.' But it does not disclose effects on Origin state — e.g., whether a workbook is imported, a graph page is created, or whether the file is modified — which matters for a plotting tool with 23 parameters and no annotation coverage.

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 sentences, front-loaded with the primary action, followed by intent guidance and the alternative recommendation. Every sentence earns its place; there is no filler or repetition of 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?

The tool is complex (23 parameters, no annotations) and the description explains the central routing model well; an output schema covers return values so those need not be described. Gaps remain: no guidance on choosing origin_plot vs. origin_plot_auto, no mention of Origin-side side effects (graph page/workbook creation), and no note on how export_path or style_mode interact with the auto flow. Adequate but not complete given the tool's 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?

Schema coverage is 100%, which sets the baseline at 3. The description adds genuine value beyond the schema by explaining when the intent parameter should be supplied and by identifying which parameters feed the auto-router (X/Y/Z and error columns). This is meaningful added semantics rather than restating the parameter 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 first sentence states a specific multi-step action — inspect table columns, select a chart route, and create the plot — naming the resource (table/file columns) and outcome (a plot). It also differentiates from the sibling origin_recommend_chart by noting that tool is used when no graph should be created yet. However, it does not contrast with the similarly named origin_plot sibling, so the 'auto-routing' distinction must be inferred.

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 concrete when-to-use guidance: provide intent when the desired comparison or relationship is known, otherwise the router falls back on column types, cardinality, and selected X/Y/Z or error columns. It explicitly names origin_recommend_chart and the condition that selects it ('when no graph should be created yet'). It does not, however, address when to prefer the explicit origin_plot tool over this automatic variant, which is the most likely source of agent confusion.

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?

Without annotations, the description carries full burden for behavioral disclosure. It does not mention that results may include recent records if no match, order, pagination, or whether the search is case-sensitive. Critical behavioral details from schema (like default limit) are omitted.

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 core purpose concisely. It is appropriately sized for a simple tool but could benefit from additional detail without losing brevity.

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 presence of 4 parameters and an output schema, the description is too minimal. It does not explain search semantics, result ordering, or filtering behavior, which are important for effective use.

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%, so parameters are already well-documented. The description adds no extra meaning beyond the schema, so a baseline score of 3 is appropriate.

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 states 'Search the local Origin knowledge base by keyword,' which clearly identifies the action (search), resource (local knowledge base), and method (by keyword). However, it does not differentiate this tool from the sibling 'origin_browse_knowledge', which likely serves a similar purpose.

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?

No guidance is provided on when to use this tool versus alternatives like 'origin_browse_knowledge' or other search tools. The description lacks context on prerequisites, use cases, or when not to use it.

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 provided, so description must disclose behavior. It mentions 'read' but does not clarify idempotency, side effects, or access requirements. The description is too brief for a tool with no 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?

Single sentence, no fluff, front-loaded. Could be slightly more descriptive about the return format, but efficiency is good.

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 5 parameters and an output schema, the description is too minimal. It does not explain 'structured rows', row limits, or behavior when parameters are omitted. More context needed for a data-reading 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 description coverage is 100% with full parameter descriptions. The description adds no additional meaning beyond schema; baseline is 3.

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 ('Origin worksheet data as structured rows'), clearly distinguishing it from siblings like origin_write_worksheet and origin_diagnose_worksheet.

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?

No guidance on when to use this tool vs alternatives; lacks context for when not to use or prerequisites. The description is purely functional.

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 full burden but does not disclose behavioral traits like what happens when data cannot be read, how recommendations are ranked, or error handling. It only gives a high-level overview.

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, focused sentence that front-loads the core action. It could be slightly more informative without sacrificing 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 tool has 15 parameters, no annotations, and an output schema, the description is too minimal. It does not explain the recommendation logic, output format, or how to interpret results, leaving the agent under-informed.

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 baseline is 3. The description hints at some parameters (table shape, column semantics, intent) but adds little beyond the schema's parameter names 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?

The description clearly states the tool recommends chart types based on table shape, column semantics, and optional intent. It uses a specific verb ('recommend') and resource ('chart types'), differentiating from sibling tools like origin_plot which actually plot data.

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 such as origin_plot_auto or origin_plan_figure_spec. It does not mention prerequisites, exclusions, or typical 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?

With no annotations, the description carries the full burden. It discloses that include_output=True is for analyses creating worksheets and mentions backward compatibility for aliases. However, it does not explain key behaviors such as synchronous vs asynchronous execution, data mutation, permissions, or error handling, which are important for agent decision-making.

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 sentences, front-loaded with the core purpose, then a key usage note, then clarification about schema naming. Every sentence serves a purpose without redundancy or 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 complexity of 8 parameters, an output schema, and the existence of sibling tools, the description covers the main purpose and key usage pattern. It could be more complete by explaining the return format or prerequisites, but the output schema likely fills some gaps. Overall, it is adequate for a tool with good schema coverage.

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 100% coverage with each parameter described. The description adds significant value by providing concrete examples for the options parameter (e.g., polynomial_fit uses order, smooth uses method and points) and explaining the recalculate sub-option. This extra context helps the agent understand how to set analysis-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 the tool runs a supported Origin analysis and returns structured metrics or output rows. It provides specific details about using include_output with output_sheet for worksheet-creating analyses, and distinguishes this tool from siblings by focusing on analysis execution versus other operations like plotting or reading worksheets.

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 guidance on when to use include_output=True with output_sheet, and mentions that aliases are accepted for backward compatibility. However, it does not explicitly state when not to use this tool or provide alternatives from the sibling list, leaving some ambiguity about best practices.

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?

Describes rendering to temp PNG, returning as image content block with text summary, and deleting temp file. Mentions max_width bounds token cost. No annotations provided, so description carries the burden well. Could explicitly state read-only behavior, but overall transparent.

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 with no fluff. Front-loaded with purpose. Student if additional details needed, but highly 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?

No output schema, but description explains return format (image + text summary). Covers parameters, behavior, and distinction from sibling. Minor missing details about summary content but adequate for selection.

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%, so baseline is 3. Description adds meaningful context: max_width limits pixel width for token cost, graph_name usage (active graph or new page). Exceeds 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?

Description clearly states 'Render an Origin graph and return it as an image the model can see.' It uses a specific verb-resource pair and distinguishes itself from sibling origin_export_graph by noting no file is left behind.

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 says 'Use it to visually verify a plot and iterate on it.' Contrasts with export_graph to guide selection. Mentions vision-capable client requirement. Doesn't list all alternatives, but provides clear 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?

With no annotations provided, the description must fully disclose behavioral traits. It only states the basic operation, omitting key details like whether data is appended or overwritten, error handling, required permissions, or what happens when the worksheet doesn't exist (though a 'create' parameter exists, its behavior is not explained in the description). This is insufficient for a mutation tool.

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, well-formed sentence with no extraneous words. It is concise and front-loaded with the core purpose.

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 presence of an output schema, return values need not be explained. However, the description lacks behavioral context (e.g., overwrite vs. append) and does not mention the tool's interaction with active sheets/workbooks, leaving the agent uncertain about side effects. It is minimally adequate but incomplete for safe autonomous use.

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 no extra meaning beyond the schema; it merely restates 'structured rows' without clarifying the interplay between 'rows', 'columns', and 'start_col' or the implications of 'create'.

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 action ('Write structured rows') and the resource ('into a new or existing Origin worksheet'), using a specific verb+resource pattern that distinguishes it from sibling tools like origin_read_worksheet or origin_diagnose_worksheet.

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, nor any exclusions or prerequisites. Sibling tools like origin_read_worksheet or origin_diagnose_worksheet appear in the list, but no differentiation is offered.

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