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

With no annotations provided, the description carries the full burden. It discloses that this is a read-only operation ('View') and describes the return format ('formatted JSON'), but lacks details on permissions, rate limits, or error behavior. It adds some context about what data is included, which is helpful but not comprehensive.

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

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

The description is front-loaded with the core purpose, followed by specific details in bullet-like structure, and ends with return information. Every sentence adds value without redundancy, making it efficient and well-organized.

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 (configuration viewing with multiple data points), no annotations, and an output schema present, the description is mostly complete. It lists what data is shown and the return format, but could improve by mentioning sibling differentiation or behavioral constraints like authentication needs.

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

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

The tool has 0 parameters with 100% schema description coverage, so no parameter documentation is needed. The description correctly doesn't discuss parameters, earning a high baseline score for not adding unnecessary information.

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 ('View current conclave configuration') and lists the exact resources it shows (member models, chairman info, presets, thresholds, API key status, custom selection). It distinguishes from siblings like 'conclave_estimate' or 'conclave_reset' by focusing on configuration viewing rather than estimation or resetting.

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 like 'conclave_models' (which might show models only) or 'conclave_full' (unclear purpose). It implies usage for viewing configuration but doesn't specify scenarios, prerequisites, or 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 are provided, so the description carries the full burden. It discloses that the tool provides 'approximate cost breakdown' and estimates based on token count, which adds useful behavioral context. However, it doesn't mention potential limitations like accuracy, rate limits, or authentication needs, leaving gaps for a tool with 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?

The description is appropriately sized and front-loaded: the first sentence states the core purpose, followed by brief elaboration. Every sentence adds value without redundancy, and the structure with 'Args:' and 'Returns:' sections enhances readability without unnecessary verbosity.

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 2 parameters with 0% schema coverage and an output schema present, the description is mostly complete. It explains parameters and return values ('Cost estimates for each query type'), but could benefit from more detail on behavioral aspects like error handling or prerequisites, especially since no annotations are provided.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning beyond the schema by explaining that 'question' is 'used to estimate token count' and 'tier' specifies 'quick/ranked/full query types' with a default of 'all'. This clarifies parameter purposes, though it doesn't detail format constraints or examples.

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: 'Estimate cost for a conclave query before running it.' It specifies the verb ('estimate'), resource ('cost'), and scope ('before running it'), distinguishing it from sibling tools like conclave_quick or conclave_full that likely execute queries rather than estimate costs.

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 for when to use this tool: 'before running it' implies it's for pre-execution cost estimation. However, it doesn't explicitly state when not to use it or name alternatives among siblings, such as comparing to conclave_config or conclave_select, which might have overlapping or related purposes.

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

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

With no annotations provided, the description carries the full burden and does well by explaining the multi-stage process ('collects opinions, peer rankings, then has a Chairman model synthesize'), the override behavior with custom conclaves, and what the tool returns. It doesn't mention rate limits, auth needs, or error conditions, but provides substantial behavioral context beyond basic functionality.

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 appropriately sized and front-loaded with the core purpose first. The Args and Returns sections are well-structured. Some sentences could be slightly more concise, but overall it's efficient with zero wasted text.

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 (multi-stage synthesis with overrides), no annotations, and 0% schema coverage, the description provides complete context. It explains the process, parameter semantics, conditional behavior, and return values. The output schema exists, so the description appropriately doesn't need to detail return structure.

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

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

With 0% schema description coverage, the description fully compensates by explaining all 4 parameters in detail: what 'question' is for, the meaning of 'tier' values, what 'chairman' overrides, and the purpose of 'chairman_preset' options. It also clarifies conditional behavior ('Ignored if custom conclave is active') that isn't in 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's purpose with specific verbs ('Run the full conclave with synthesis') and resources ('all 3 stages'), and distinguishes it from siblings by emphasizing it's the 'most comprehensive' option that includes synthesis. It explicitly mentions what makes it different from other conclave 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 provides explicit guidance on when to use this tool ('Most comprehensive') and when parameters are ignored ('Ignored if custom conclave is active'). It also implies alternatives through sibling tool names like conclave_quick and conclave_ranked, giving clear 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 provided, the description carries the full burden and does well by disclosing key behavioral traits: it lists models grouped by tier, specifies that numbers are stable with defined ranges per tier, and describes the return format as a numbered list. It doesn't mention aspects like rate limits or authentication needs, but covers essential behavior adequately for a read-only 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 front-loaded with the core purpose in the first sentence, followed by supporting details in bullet points and a returns section. Every sentence earns its place by adding specific information about tiers, number stability, and usage context without any redundant or vague statements.

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 (0 parameters, no annotations, but with an output schema), the description is complete. It explains the purpose, behavioral context (stable numbers per tier), usage with 'conclave_select', and return format. The output schema likely details the structure, so the description doesn't need to exhaustively list return values, making it well-rounded for this context.

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

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description appropriately focuses on output semantics, explaining the numbered list structure and tier groupings. This adds value beyond the schema by clarifying what the tool returns, which is helpful given the presence of an output 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 verb 'List' and resource 'all available models with selection numbers', specifying it shows models from all tiers with unique numbers. It distinguishes from siblings by mentioning these numbers are used with 'conclave_select' to create custom conclaves, providing specific differentiation.

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 by explaining that the numbers are used with 'conclave_select' for custom conclave creation, giving a specific when-to-use scenario. However, it doesn't explicitly state when not to use this tool or compare it to alternatives like 'conclave_quick' or 'conclave_full', which could help further differentiate usage.

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 and does well by disclosing key behavioral traits: it's 'Fast and cheap', queries 'all conclave models in parallel', returns 'individual responses' without synthesis, and mentions the interaction with conclave_select for custom conclaves. It doesn't cover rate limits, authentication needs, or error handling, but provides substantial operational 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 perfectly structured and concise: purpose statement first, key characteristics next, behavioral notes, then parameter details in labeled sections. Every sentence earns its place with no redundancy or fluff. The use of sections (Args, Returns) enhances readability.

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 2 parameters with 0% schema coverage and no annotations, the description does an excellent job explaining parameters and behavioral context. The existence of an output schema means it doesn't need to detail return values. It could mention more about error cases or prerequisites, but covers the essential context well for this query 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 0%, so the description must compensate. It adds meaningful semantics for both parameters: 'question' is described as 'The question to ask the conclave', and 'tier' gets detailed explanation of values ('premium', 'standard', 'budget') with defaults and the override rule when custom conclave is active. This goes well beyond the bare 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's purpose with specific verbs ('Query the conclave for quick parallel opinions') and distinguishes it from siblings by specifying 'Stage 1 only', 'Fast and cheap', 'No peer ranking or synthesis', and 'Good for getting diverse perspectives quickly'. It explicitly differentiates from tools like conclave_full or conclave_ranked that likely involve synthesis or ranking.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool ('Good for getting diverse perspectives quickly') and when not to use it ('Stage 1 only', 'No peer ranking or synthesis'). It also mentions the alternative of using a custom conclave via conclave_select, though it could be more explicit about other sibling alternatives like conclave_full or conclave_ranked.

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

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: the two-stage process (individual opinions then anonymous ranking), cost level ('medium cost'), and the effect of 'conclave_select'. However, it doesn't cover important aspects like rate limits, authentication needs, error handling, or what 'street cred' scores entail, leaving gaps for a tool with no annotation support.

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 appropriately sized and front-loaded, starting with the core purpose. The sentences are efficient, but the 'Args' and 'Returns' sections could be integrated more seamlessly, and some phrasing ('medium cost') is slightly vague, slightly reducing 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 complexity (multi-stage ranking process), no annotations, and an output schema present, the description is mostly complete. It covers the process, parameters, and return overview, but lacks details on output structure or error cases, which the output schema might handle, making it adequate but not fully 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 description coverage is 0%, so the description must compensate. It explains 'question' as 'the question to ask the conclave' and 'tier' with values and default, adding meaning beyond the bare schema. However, it doesn't detail format constraints for 'question' or fully explain 'tier' implications beyond the list, resulting in partial compensation for the low coverage.

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

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

The description clearly states the tool 'queries the conclave with peer rankings' and specifies it involves 'Stage 1 + 2' processing, which distinguishes it from simple query tools. However, it doesn't explicitly differentiate from siblings like 'conclave_full' or 'conclave_quick' in terms of ranking methodology, leaving some ambiguity about sibling differentiation.

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 for usage: it mentions 'medium cost' and explains when to use it (for getting individual opinions and aggregate rankings). It also notes that a custom conclave via 'conclave_select' overrides the tier parameter, offering some alternative guidance. However, it lacks explicit when-not-to-use scenarios or comparisons to specific siblings like 'conclave_estimate' or 'conclave_quick'.

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 and does well by disclosing the behavioral outcome ('clear custom selection', 'return to tier-based config', 'queries will use tier parameter') and return value ('Confirmation that custom selection was cleared'), though it lacks details on permissions or 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?

It is front-loaded with the core action in the first sentence, followed by outcome and return details in clear, efficient sentences. Every sentence adds value without waste, making it highly 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?

Given the tool's simplicity (0 parameters, no annotations, but has output schema), the description is nearly complete by explaining the reset action, post-reset behavior, and return value. It could slightly improve by mentioning any prerequisites or errors, but covers essentials well.

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

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

The tool has 0 parameters with 100% schema description coverage, so no parameter info is needed. The description appropriately focuses on behavior and output, earning a baseline 4 for not adding unnecessary details beyond the empty 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 ('Clear custom conclave selection') and the resource affected ('tier-based config'), distinguishing it from siblings like conclave_config or conclave_select that likely configure or choose models rather than resetting to defaults.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It implicitly indicates usage context ('return to tier-based config') and the effect ('queries will use the tier parameter'), but does not explicitly state when to use this vs. alternatives like conclave_config or what triggers a reset need, missing explicit exclusions or prerequisites.

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

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

With no annotations provided, the description carries the full burden and does so well. It discloses key behavioral traits: the custom selection persists until server restart or conclave_reset, the first model becomes chairman, and it references sibling tools (conclave_models, conclave_reset) for context. It doesn't mention permissions, rate limits, or error handling, but covers persistence and structure adequately.

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

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

The description is well-structured and front-loaded with the core purpose, followed by usage details, persistence, args, returns, and an example. Every sentence adds value without redundancy, and the example efficiently illustrates the tool's behavior.

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 (custom conclave creation with persistence), no annotations, and an output schema present, the description is complete. It covers purpose, usage, parameters, behavioral traits, and includes an example, making it sufficient for an AI agent to understand and invoke the tool correctly.

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

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

The schema description coverage is 0%, so the description must compensate, which it does excellently. It explains the 'models' parameter as comma-separated model numbers, specifies the first number is chairman and the rest are members, provides an example format, and clarifies the mapping to specific models (e.g., model #31 = deepseek-r1).

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: 'Create a custom conclave from model numbers' with specific actions like selecting models and designating a chairman. It distinguishes from siblings by focusing on custom selection rather than configuration, estimation, or resetting.

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 for when to use this tool: to create a custom conclave from specific model numbers, with the first model as chairman. It mentions persistence until server restart or conclave_reset, but does not explicitly state when to use alternatives like conclave_quick or conclave_ranked.

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