Minds: Synthetic Market Research Panels

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

Beyond the annotations, the description reveals important behavioral traits: it creates a private one-Group Panel, starts asynchronous responses, and returns a Panel identifier with status links. This accurately conveys side effects and return information.

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 dense sentences with no filler. The first sentence states the core action, and the second covers identification, side effects, and return value.

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 no output schema, the description explains the return artifact (Panel identifier and status links), asynchronous nature, and group resolution options. This is complete for an agent to invoke and follow up on the operation.

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?

Even though schema coverage is 100%, the description adds meaningful semantics: groupId vs groupName as exact vs fuzzy identification, question is respondent-visible with safety warning about not including planner instructions, and attachments are processed once and shared with every group member. This is genuinely additive.

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 uses specific verb 'Submits' with resource 'single existing Group' and clarifies it creates a one-Group Panel, distinguishing it from sibling tools like ask_panel. The scope (one question, one group) 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?

Clear use context is provided: ask a single existing group, identify by ID or fuzzy name, asynchronous responses. However, it does not explicitly mention when not to use it or name alternatives such as ask_panel for existing panels.

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

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

Beyond annotations (readOnlyHint:false, openWorldHint:true), the description adds key behavioral details: responses are asynchronous, the question value may reach respondents and is not planner-only metadata, question types are auto-classified, and the response includes status/workspace links. No contradiction with annotations; this is valuable additional context.

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 dense sentences, front-loaded with the core action, and every sentence contributes distinct information. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 parameters, no output schema, and async behavior, the description covers the essential return info (status and workspace links) and clarifies the respondent-visible nature. The schema handles parameter details. Slight gap: no mention of error conditions or limitations, but not necessary for tool 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 description coverage is 100%, so the schema fully documents all parameters. The description adds a small amount of emphasis on the question being respondent-visible, but does not go beyond the schema's own detailed descriptions. 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 opens with a specific verb ('Submits') and resource ('an existing Panel'), clearly stating the tool starts asynchronous responses from Minds. It explicitly distinguishes from siblings by noting this operation 'does not create or enumerate Panels', making the 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 states that follow-up questions remain within the existing Panel and explicitly excludes create/enumerate operations, providing clear when-to-use context. It does not name specific alternative tools, but the exclusion and context are strong enough to guide tool 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 adds behavioral details beyond the annotations: it persists provenance and allocation audits, is idempotent for identical inputs (mirroring idempotentHint), keeps the group private unless link sharing is enabled, and supports multiple sizing modes. It does not contradict the annotations and provides meaningful extra context.

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 front-loads the core action and packs in multiple behaviors without filler. Though dense, it remains readable and every phrase earns its place, making it appropriately concise for a complex tool.

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 12 parameters, nested objects, and no output schema, the description covers high-level behavior well but omits return values and edge cases like silent plan downgrades (though the schema mentions this). It is solid for selection but not fully complete for invoking without looking at schema 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?

Schema description coverage is 100%, with exceptionally detailed per-parameter descriptions including nested objects. The description's mention of sizing modes adds no new syntax beyond what groupCreationMode already explains, so it meets the baseline without needing to compensate.

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 'Creates a grounded Group of synthetic Minds from a population or audience brief,' clearly stating the verb, resource, and source. It distinguishes itself from siblings like create_panel and ask_group by focusing on 'group from a brief' and explicitly enumerating its capabilities.

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 strong usage context: it is for creating a grounded group from a brief, optionally augmented by web research, files, links, and spreadsheet distributions. However, it does not explicitly name alternatives or state when not to use this tool, so it falls short of a 5.

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

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

The description adds significant behavioral context beyond annotations: composite creation is atomic and rolls back partial Group failures, Panels are private by default, and enabling link sharing publishes attached Groups and Minds. These are critical side effects not visible in the annotations, making the tool's behavior 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?

The description is three sentences, with the primary purpose in the first sentence, usage guidance in the second, and key behavioral caveats in the third. Every sentence adds distinct value, and the structure front-loads the most important information.

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 creation tool with no output schema, the description covers essential behavioral aspects like atomicity, privacy, and the side effect of publishing attached Groups and Minds. It does not state what the tool returns on success (e.g., panel ID), but this is not critical given the action-oriented nature. Slight completeness gap for return value.

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% parameter description coverage, so the schema carries the heavy lifting. The description reinforces the distinction between existing Groups and inline Group configurations but does not add new parameter-level semantics beyond what the schema already explains, such as the warning on isLinkSharingEnabled.

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 creates a new research Panel from existing Groups or inline Group configurations, with an explicit scope qualifier 'when the intended outcome is a new Panel.' This distinguishes it from sibling tools like create_group_from_brief and ask_panel, and also clarifies that follow-up research on an existing Panel is not a use case.

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 explicit when-to-use ('when the intended outcome is a new Panel') and when-not-to-use ('Follow-up research on an existing Panel does not require creation') guidance. However, it does not name alternative tools or provide conditional exclusions beyond the follow-up case, so it stops 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 adds useful behavioral details beyond annotations: it lists supported formats (Markdown, PDF, DOCX, PPTX) and states that binary artifacts are returned as base64. This complements the idempotentHint annotation by clarifying output encoding, with no contradiction to 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 three short sentences, front-loaded with the verb and resource. Each sentence adds distinct information: purpose, formats, and output encoding, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple export operation, the description covers all essential aspects: target (group brief), rendering context, supported formats, and base64 return. The absence of an output schema is mitigated by explicitly stating the base64 artifact format, and the schema covers parameter 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?

All four parameters are already described in the input schema (100% coverage), so the description need not add parameter details. The description does not mention parameters directly, but the schema handles their semantics; the mention of formats overlaps with the format enum without adding new meaning.

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 exports a group brief and specifies the rendering mechanism (unified branded renderer) and supported formats. This distinguishes it from sibling export tools like export_panel and export_heatmap, which target different resources.

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 does not explicitly state when to use this vs. sibling export tools (export_panel, export_heatmap). The name and resource hint at usage for group briefs, but no exclusion 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?

Annotations already indicate idempotence and non-destructiveness; the description adds the return format (ZIP with unified-renderer PDF, Markdown, images, metadata) and the requirement that the panel be completed, which is useful beyond the structured 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?

Two efficient sentences, front-loaded with the verb and resource, then return contents. 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?

For a tool with no output schema, the description clearly specifies the required input (message ID from completed panel results) and expected output (ZIP archive contents). It does not cover error cases, but these are not essential for invoking 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?

Schema description coverage is 100% and already details all parameters. The description only restates that the message ID identifies the completed panel result, adding minimal 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 clearly states the tool exports a completed website heatmap from a panel message using a message ID, distinguishing it from sibling export tools (export_panel, export_mind, export_group) which handle different resources.

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 tool is used when a panel's completed results include a heatmap and you have the reported message ID. It does not explicitly list alternatives or when-not-to-use, but the specific source and resource make the usage context 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?

Annotations already supply idempotent and non-destructive hints; the description adds meaningful behavior about inline markdown vs base64 artifacts with workspace link and the default format. This extends beyond the structured data without contradiction.

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

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

Two dense, front-loaded sentences with no filler. Effectively conveys purpose and output behavior in a compact, structured way.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, identification, and output formats, with annotations and schema filling gaps like force/caching. Omits explicit error handling or what happens if no identifier is provided, but the description is adequate for selection and invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema covers all 4 parameters with descriptions, so the description adds minimal additional semantics. The phrase 'exact ID or fuzzy name' mirrors the schema's 'UUID' and 'fuzzy matched' descriptions, and the default format is already noted in the format enum 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?

Clearly states it generates a branded profile for an existing Mind, using specific verb 'Generates' and resource 'branded profile for one existing Mind'. The mention of 'Mind' distinguishes it from sibling export_group/export_panel 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?

Provides clear context that this tool is for one existing Mind and supports exact ID or fuzzy name, but does not explicitly contrast with alternative export tools. The resource-specific wording offers enough 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 discloses the asynchronous nature and the job ID return, which are critical behavioral details beyond the annotations (readOnlyHint=false, idempotentHint=true). It also hints at format/kind compatibility restrictions, adding useful context.

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 concise sentences, front-loaded with the core action and return value. Every sentence serves a purpose, with 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?

For a complex async export tool with 6 parameters and no output schema, the description covers the core action, return value, supported formats, and kinds. It lacks explicit guidance on tracking the job (e.g., using get_panel_status), but the sibling list and 'returns an export job ID' make this reasonably inferable.

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 provides thorough descriptions for all 6 parameters (100% coverage), including enum values and defaults. The description adds minimal extra meaning beyond restating supported kinds and formats, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Starts an asynchronous export'), the resource ('Panel results'), and the return value ('export job ID'). It distinguishes from sibling export tools by targeting Panel results specifically.

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 context for when to use the tool: when exporting Panel results. It does not provide explicit exclusions or mention alternatives like export_heatmap, but the scope is unambiguous given the focus on Panel results.

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 convey read-only, idempotent, and non-destructive behavior. The description adds useful context about live progress and the conditional return of export job status when export identifiers are supplied. No contradiction with 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 a single, dense sentence with no filler. Every phrase contributes meaningful information, and the main verb and result list are front-loaded for quick scanning.

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 tool with no output schema, the description enumerates all major return categories and the conditional export status. Panel selection rules are covered in the schema, so the description is sufficiently complete, though it does not detail output structure or edge cases like absent data.

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 provides 100% coverage with detailed descriptions for all five parameters, including the default behavior for exportKind and exportFormat. The description does not add extra parameter semantics beyond mentioning 'export identifiers'.

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 returns current Panel state, live progress, per-Group results, linked Minds, Panel links, and export job status. This specific enumeration distinguishes it from sibling tools like get_panel_summary or get_panel_study.

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 based on the listed return items, but provides no explicit guidance on when to choose this tool over alternatives such as get_panel_summary or export_panel. The conditional export-job status is mentioned, but no when-to-use or exclusions are stated.

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 read-only expectation is covered. The description adds meaningful context beyond annotations by specifying the immutable nature of the confirmed plan and the durable character of results, enriching the agent's understanding without contradicting any hints.

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, information-dense sentence that enumerates seven distinct result categories without extraneous words. It could be slightly more structured (e.g., numbering the list) but every phrase carries meaning, making it efficient 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?

With no output schema, the description carries the burden of explaining return values. It does this thoroughly by listing plan, audit, progress, artifacts, calculations, and readiness. It does not clarify when results become available or error conditions, but for a status retrieval tool, the listed context is sufficient for an agent to predict the tool's output.

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 coverage is 100% with descriptions for all three parameters (panelId, studyId, panelName). The tool description does not add parameter-specific meaning, which is acceptable given the schema already documents them fully. Baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool 'Returns durable progress or results for a Panel study' and lists specific components returned (confirmed plan, execution plan, audit, progress, artifacts, calculations, readiness). This distinguishes it from sibling tools like get_panel_status that target the panel itself, not the study.

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 context that this tool is for retrieving durable progress/results of a Panel study, which implies when to use it. However, it does not explicitly mention alternatives or exclusions relative to sibling tools (e.g., get_panel_status, run_panel_study), so it misses the explicit guidance that would earn a 5.

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

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

Annotations indicate readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds meaningful context by noting 'Returns or refreshes,' aligning with the non-read-only annotation, and by specifying the output format and heatmap-compatible metadata. It does not contradict annotations and enriches them with behavioral details.

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 concise sentences, front-loaded with the primary action ('Returns or refreshes'), and includes useful detail about output format and metadata. Every sentence earns its place, with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description must convey return structure, but it only vaguely mentions 'flexible evidence blocks' without explaining their composition or how length affects output. It does clarify refresh behavior and panel context via schema, but overall the description leaves moderate gaps for a tool with five parameters.

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 80% (4 of 5 parameters described), so the schema handles most parameter semantics. The description mentions 'heatmap-compatible block metadata' which relates to output rather than parameters, adding minimal parameter-specific value. 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 the tool returns or refreshes a semantic summary for a Panel study, distinguishing it from siblings like get_panel_study. It mentions specific output (Markdown plus evidence blocks), but does not explicitly differentiate from alternatives, so not a 5.

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 such as get_panel_study or export_panel. There are no mentions of prerequisites, exclusions, or specific scenarios, leaving the agent to infer usage from the name alone.

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

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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds operational details: return contents (member Minds, sharing state, links) and the optional fuzzy name search parameter, which enrich the agent's understanding beyond the structured 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 front-loaded, with the main purpose in the first sentence. Each additional sentence adds value: one explains the optional search, the other clarifies synonymous terms for 'groups', helping semantic matching without bloat.

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 with one optional parameter and no output schema, the description covers essential aspects: what the tool returns (member Minds, sharing state, links), the search filter, and scope. Also provides synonyms to avoid ambiguity in interpretation.

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% for the searchQuery parameter, which already has a clear description. The description restates 'optional fuzzy name search' but adds no new semantic detail beyond what the 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 the tool 'Lists the authenticated user's Groups' with specific scope and what is included (member Minds, sharing state, links). The verb 'Lists' distinguishes it from sibling tools like ask_group, export_group, and create_group.

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 is implied by the action ('Lists') and scope ('authenticated user's'), making it clear when to use for listing groups. However, it does not explicitly mention alternatives or when-not conditions, leaving nuanced choice to the agent.

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, idempotentHint, and destructiveHint false, so safety is covered. The description adds value by specifying exactly what is returned (Groups, Minds, status, sharing state, links) and the fuzzy search behavior, exceeding the minimal 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?

The description is two well-structured sentences. The first sentence front-loads the action and scope, while the second adds useful synonyms. 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 read-only list operation with one optional parameter and no output schema, the description covers purpose, scope, returned entities, search capability, and terminology. It is sufficiently complete for an agent to select and invoke the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes the only parameter (searchQuery) with fuzzy matching already noted. The description restates this without adding new detail, so it meets the baseline of 3 where schema coverage is high.

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 the authenticated user's Panels with specific associated data (Groups, Minds, status, sharing state, and links). It distinguishes itself from sibling list tools by focusing on Panels and their sub-entities, and includes synonyms to disambiguate terminology.

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: it lists the user's panels with optional fuzzy search. It does not explicitly name alternatives or exclusions, but the context makes it obvious when to use it (for panel listing) versus sibling tools like list_groups.

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 the tool as read-only and idempotent. The description adds valuable context by specifying the output includes executable status, availability, complexity, and fallback metadata, and that results distinguish executable from planned methods. This goes beyond the structured annotations without contradicting them.

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

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

The description is two sentences with no filler. It front-loads the primary action ('Lists Minds research methods') and then clarifies the output distinction, making it concise and well-structured.

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 list tool with one optional parameter and no output schema, the description adequately conveys the tool's purpose, output traits, and key distinctions. The annotations cover safety and idempotence, so the description doesn't need to repeat those, leaving the description complete for its 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 description coverage is 100% for the only parameter (includePlanned), which is fully documented including dynamic availability. The main description does not add parameter-specific meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists research methods and enumerates the metadata categories (availability, complexity, executable status, fallback metadata). It also distinguishes executable methods from experimental/planned ones, making the purpose unambiguous and distinct from sibling list 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 implies usage for listing research methods but does not explicitly state when to use it versus alternatives. The schema adds a hint that setting includePlanned helps explain framework compatibility, but the description itself offers no explicit exclusions or comparisons to sibling tools.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds behavioral context by clarifying the dual mode (list vs. single retrieval) and the durable/unfinished nature of drafts, plus the distinction from running/completed studies. No contradiction with 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 two sentences, front-loaded with the main purpose, and contains no redundant or filler content. It efficiently conveys both modes of operation and the key distinction from other study states.

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 one optional parameter, no output schema, and strong annotations, the description fully covers the tool's behavior. It explains the list vs. single-draft retrieval modes and the draft vs. study distinction, leaving no significant 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?

The input schema provides 100% parameter coverage with a clear description for draftId, including the omit-to-list behavior. The description's mention of 'one exact draft ID' adds no new semantic value beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it lists durable unfinished study drafts or retrieves a single draft by ID, and explicitly distinguishes drafts from running/completed studies. This differentiates it from sibling tools like run_panel_study and get_panel_study.

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 context by noting drafts are distinct from running/completed studies, implying use when drafts are needed. However, it does not explicitly name alternative tools or state when not to use this tool, so it lacks explicit exclusion guidance.

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 no safety hints (readOnlyHint, destructiveHint, etc.), so the description carries the burden. It discloses the key non-executing behavior and that it doesn't start research, but doesn't reveal side effects like whether revisions overwrite prior drafts, whether confirmation answers are required, or persistence behavior.

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

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

Three concise sentences, front-loaded with the core purpose, followed by the draft contents and a clear exclusion. 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?

Although the schema is rich, there is no output schema and the description doesn't explain the interactive workflow (e.g., that the tool returns confirmation questions or a draft for review) or what the response looks like. The 'does not start research' is helpful but missing return-value and workflow 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 input schema has 100% description coverage, with detailed parameter descriptions (e.g., request, source, questionResponses). The description's mention of 'response formats, locale, method' adds little beyond what the schema already specifies, 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?

Clearly states it creates or revises a non-executing draft for a Panel study, using specific verbs and resource. It distinguishes from run_panel_study by explicitly saying 'does not start research' and describing the draft contents.

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 'It does not start research,' which tells the agent when not to use this tool (use run_panel_study instead). It also implies use for creating or revising drafts, but doesn't name alternatives like save_study_draft or ask_panel. Sufficient but not exhaustive.

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

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

Beyond annotations (which indicate a non-read-only, idempotent, non-destructive operation), the description discloses specific validation steps ('reloads and validates the revision, method availability, runner configuration, reviewed capabilities, optional advanced-method consent, and idempotency key') and that it 'queues durable research,' adding meaningful behavioral context without contradicting 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 a single, focused sentence with the core action front-loaded, followed by necessary validation/behavior details. No extraneous information or repetition; it earns every word.

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 parameter-rich tool (8 params) with no output schema, the description covers the core flow: exact draft revision, confirmation requirement, server validation steps, and queuing. It omits explicit return-value/response details, but the validation steps and preconditions are well communicated, making it mostly 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% with clear per-parameter descriptions (e.g., draftPlanId 'returned by plan_panel_study', confirmed 'must be true only after user explicitly confirms'). The tool description reinforces these concepts but does not add semantic meaning 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?

Description uses a specific verb+resource: 'Executes an exact stored Panel-study draft revision after explicit confirmation.' This clearly distinguishes from sibling tools like plan_panel_study (planning) and save_study_draft (saving), making the execution/run 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 establishes clear usage context: this tool runs an exact stored draft revision only after explicit confirmation, and the server validates several preconditions before queuing. It does not explicitly name alternatives or exclusions, but the context implies it is the execution step following draft creation/confirmation.

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 indicate non-read-only, non-idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: it states what data is saved, that revisions require exact draft ID and revision, and that stale writes are rejected. This provides a clear picture of the optimistic concurrency behavior without contradicting 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 (two sentences), front-loaded with the main purpose, and each sentence carries essential information—what the tool does and its revision safety mechanism. There is no redundancy or filler.

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 (12 parameters), the description provides a high-level but sufficient overview of the workflow: creating/checkpointing drafts, saving various study components, and handling revisions. It doesn't detail every field or explain return values, but the rich schema compensates for that. The concurrency behavior is clearly highlighted, which is critical for correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents every parameter's meaning. The description adds marginal value by grouping parameters (objective, context, selected Audiences, method, questions, sources, current planner step) and explicitly describing the expectedRevision behavior. This aligns with the baseline of 3, as the description doesn't significantly enhance parameter understanding 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 specific action ('Creates or checkpoints'), the resource ('unfinished Quick or Custom Study draft'), and the key scope ('without starting research'). It differentiates from sibling tools like run_panel_study by explicitly noting that research is not started.

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 indicates when to use the tool (for creating or checkpointing drafts) and provides critical guidance for revisions ('Revisions require the exact draft ID and expected revision, and stale writes are rejected'). It also implies when not to use it ('without starting research'). However, it doesn't explicitly name alternative tools for different scenarios.

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