Pythia MCP

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 what the tool does but doesn't describe output format, computational characteristics, error handling, or whether this is a read-only analysis versus something that modifies state. For a physics analysis tool with 4 parameters, this is inadequate.

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 concise - one sentence that efficiently conveys the core functionality and supported variants. Every word earns its place with no redundancy or unnecessary elaboration.

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 physics analysis tool with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the analysis produces (coupling values? constraints? comparisons?), how results are formatted, or what users can expect from invoking this tool. The context demands more completeness.

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 all parameters thoroughly. The description adds minimal value beyond what's in the schema - it mentions supported variants which relates to the 'type' parameter but doesn't provide additional context about parameter interactions or interpretation of results.

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: analyzing Two-Higgs-Doublet Model parameters in terms of Higgs couplings. It specifies the resource (2HDM parameters) and action (analyze), but doesn't explicitly differentiate from siblings like 'analyze_singlet_extension' or 'compute_sm_predictions' beyond mentioning supported variants.

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 about when to use this tool versus alternatives. The description mentions supported variants but doesn't explain when to choose this over sibling tools like 'analyze_singlet_extension' for different models or 'compute_sm_predictions' for Standard Model comparisons.

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 lacks behavioral details. It doesn't disclose whether this is a read-only or computational operation, potential side effects, performance characteristics, or output format. The description only states what is analyzed, not how it behaves.

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, zero waste, front-loaded with the core purpose. Every word earns its place without redundancy or unnecessary elaboration.

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 computational physics tool with 2 parameters, no annotations, and no output schema, the description is incomplete. It doesn't explain what the analysis produces, computational requirements, or how results should be interpreted, leaving significant gaps for an AI agent.

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 both parameters. The description doesn't add any parameter-specific information beyond what's in the schema, such as typical value ranges or physical interpretation context. Baseline 3 is appropriate when 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 clearly states the action ('Analyze') and the target ('Higgs singlet extension model'), specifying the analysis focuses on mixing between SM Higgs and singlet. It distinguishes from siblings like 'analyze_2hdm' by specifying the model type, but doesn't explicitly contrast with other analysis tools like 'scan_1d' or 'scan_2d'.

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 doesn't mention prerequisites, when not to use it, or compare with siblings like 'analyze_2hdm', 'scan_1d', or 'compute_likelihood', leaving usage context implied rather than 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?

With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. It mentions the tool computes '-2 log L' but doesn't describe output format, error conditions, computational requirements, or data sources beyond 'LHC experimental data'. For a complex scientific computation tool, this is inadequate.

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 efficiently convey the core purpose without redundancy. The first sentence states what the tool does, the second provides context about its role. However, it could be more front-loaded with key behavioral information given the tool's complexity.

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 tool with 17 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what '-2 log L' means in practical terms, how results should be interpreted, what experimental data is used, or any limitations/assumptions. The context signals indicate high complexity that isn't addressed.

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 marginal value by mentioning 'reduced couplings or signal strengths' which aligns with the mode parameter, but doesn't provide additional semantics beyond what's already documented in the comprehensive schema 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's purpose with specific verbs ('compute', 'compare') and resources ('Higgs likelihood', 'theoretical predictions', 'LHC experimental data'). It distinguishes from siblings by focusing on likelihood computation rather than analysis of specific models (e.g., analyze_2hdm) or auxiliary functions like data fetching.

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 comparing theoretical predictions against experimental data but doesn't explicitly state when to use this tool versus alternatives like compute_sm_likelihood or convert_to_signal_strength. It mentions the primary analysis function but lacks explicit guidance on tool selection criteria.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool computes p-values but doesn't explain what statistical method is used (e.g., chi-squared distribution), whether it handles edge cases (e.g., invalid likelihood/ndf values), what the output format is, or any error conditions. For a statistical computation tool with zero annotation coverage, 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 a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to parse quickly. Every part of the sentence contributes to understanding the core functionality.

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 statistical computation, lack of annotations, and no output schema, the description is incomplete. It doesn't explain the statistical methodology, output format, error handling, or how it integrates with sibling tools (especially compute_likelihood). For a tool that performs mathematical calculations with multiple parameters, more 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?

Schema description coverage is 100%, so the schema already documents all three parameters thoroughly. The description adds no additional parameter semantics beyond what's in the schema (e.g., it doesn't clarify the relationship between likelihood and ndf, or how reference affects computation). With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate with extra insights.

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: 'Compute the p-value for a given model compared to the Standard Model or best-fit point.' It specifies the action (compute) and resource (p-value) with context (comparison to SM or best-fit). However, it doesn't explicitly differentiate from sibling tools like compute_likelihood or compute_sm_likelihood, which prevents a perfect score.

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. It mentions the tool computes p-values for model comparisons but doesn't indicate prerequisites (e.g., needing likelihood values from compute_likelihood), when to choose SM vs. bestfit reference, or how it differs from sibling statistical tools. This leaves usage context unclear.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool computes and returns '-2 log L for SM couplings (all C = 1)', which implies a read-only calculation, but doesn't cover critical aspects like performance characteristics, error handling, or whether it's idempotent. For a computational tool with zero annotation coverage, this leaves significant behavioral 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 extremely concise and front-loaded: two sentences that directly state the purpose and return value with zero wasted words. Every sentence earns its place by providing essential information about what the tool does and what it returns.

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 computational nature, single parameter, and lack of output schema, the description is minimally complete. It explains what's computed and the return format (-2 log L), but doesn't provide context about the significance of the result or how it fits with other tools. With no annotations and no output schema, it should ideally explain more about the computation's scope or limitations.

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 the single parameter 'expInput' documented as 'Path to experimental input list'. The description adds no additional parameter information beyond what the schema provides. According to the rules, with high schema coverage (>80%), the baseline is 3 even with no param info in the description, which applies here.

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: 'Compute the Standard Model likelihood as a reference point.' It specifies the verb ('compute') and resource ('Standard Model likelihood'), and distinguishes it from siblings like 'compute_likelihood' by specifying it's for SM couplings with C=1. However, it doesn't explicitly differentiate from 'get_sm_predictions' which might be a related sibling.

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. It doesn't mention when to choose this over 'compute_likelihood' (a sibling tool) or other analysis tools like 'analyze_2hdm'. There's no context about prerequisites, timing, or exclusions, leaving the agent without usage direction.

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

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

With no annotations provided, the description carries full burden but lacks behavioral details. It doesn't disclose whether this is a read-only calculation or has side effects, what the output format is (e.g., numerical values, structured data), error handling, or computational constraints (e.g., rate limits for physics simulations). The description only states the conversion action without 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 a single, efficient sentence that front-loads the core action ('convert') and scope. Every word earns its place—'reduced couplings', 'signal strength values', and 'all production and decay modes' are precise physics terms without redundancy. No extraneous details or fluff are present.

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 (9 parameters, physics domain), no annotations, and no output schema, the description is incomplete. It doesn't cover parameter meanings, output format, error conditions, or usage context. For a tool with significant input requirements and no structured support, more explanation is needed to guide 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 description coverage is 0%, so the description must compensate but adds no parameter information. It doesn't explain what 'mass', 'CV', 'CF', etc., represent (e.g., particle mass, coupling constants), their units, valid ranges, or interdependencies. With 9 undocumented parameters, the description fails to provide essential semantics beyond the schema's bare 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 action ('convert') and the transformation ('reduced couplings to signal strength values'), specifying the scope ('for all production and decay modes'). It distinguishes from siblings like 'compute_likelihood' or 'scan_1d' by focusing on unit conversion rather than analysis or scanning. However, it doesn't explicitly differentiate from tools like 'get_sm_predictions' which might involve similar physics concepts.

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. It doesn't mention prerequisites (e.g., needing coupling values first), exclusions, or comparisons to siblings like 'compute_sm_likelihood' for related calculations. Usage is implied only by the conversion purpose, with no explicit 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 full burden but only states what the tool does, not behavioral traits like authentication needs, rate limits, error handling, or what 'detailed data' includes. It mentions fetching by specific identifiers but lacks context on permissions or data freshness.

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, efficient sentence that front-loads the purpose with no wasted words. It directly communicates the tool's function and key parameters without unnecessary elaboration.

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 4 parameters, 100% schema coverage, and no output schema, the description is minimally adequate. It clarifies the tool's focus on specific records but lacks details on return values, error cases, or integration with sibling tools, leaving gaps in contextual 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds no additional meaning beyond implying that 'inspireId' and 'recordId' are alternative identifiers, which is somewhat redundant with the schema. Baseline 3 is appropriate as the 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 clearly states the action ('fetch detailed data') and resource ('specific HEPData record'), specifying it works by INSPIRE ID or record number. It distinguishes from siblings like 'search_hepdata' (which likely searches broadly) by focusing on fetching a specific record, though it doesn't explicitly mention this distinction.

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 when you have a specific record identifier (INSPIRE ID or record number), but doesn't explicitly state when to use this versus alternatives like 'search_hepdata' or 'get_dataset_info'. 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 states the tool retrieves metadata but does not disclose behavioral traits such as whether it's read-only, requires authentication, has rate limits, or what the output format looks like (e.g., JSON structure). This leaves significant 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 a single, efficient sentence that front-loads the core purpose ('Retrieve detailed metadata') without any wasted words. It is appropriately sized for a simple retrieval 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 the tool's low complexity (single parameter, no nested objects) and high schema coverage, the description is minimally adequate. However, with no output schema and no annotations, it fails to explain return values or behavioral aspects, leaving the agent with incomplete context for proper 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?

The schema description coverage is 100%, with the parameter 'recid' fully documented in the schema. The description adds no additional meaning beyond the schema, such as examples or constraints on the record ID format. Baseline 3 is appropriate as the schema handles parameter documentation.

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

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

The description clearly states the specific action ('Retrieve detailed metadata') and resource ('for a specific CERN Open Data record'), distinguishing it from siblings like 'list_cern_opendata_files' (which lists files) and 'search_cern_opendata' (which searches). It precisely identifies the operation as retrieval by record ID.

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

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

The description implies usage context by specifying 'by its record ID,' indicating this tool is for fetching a known record rather than searching or listing. However, it does not explicitly state when to use alternatives like 'search_cern_opendata' or 'list_cern_opendata_files,' missing explicit exclusions or comparisons.

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 full burden. It mentions what information is returned but doesn't disclose behavioral traits such as whether this is a read-only operation, potential rate limits, authentication needs, error conditions, or response format. For a tool with no annotations, this leaves significant gaps in understanding how it behaves.

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, efficient sentence that front-loads the purpose and key details. Every word earns its place, with no redundant information or fluff, making it easy to parse quickly.

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 no annotations and no output schema, the description provides basic purpose and return content but lacks completeness for a tool that likely returns complex data. It doesn't cover behavioral aspects, error handling, or output structure, which are important for an agent to use it correctly in 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?

Schema description coverage is 100%, with the parameter 'datasetPath' fully documented in the schema. The description doesn't add any parameter-specific semantics beyond what the schema provides (e.g., it doesn't explain path formats or constraints further). Baseline 3 is appropriate since the schema handles parameter documentation.

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

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

The description clearly states the verb 'Get' and the resource 'detailed information about a specific experimental dataset', specifying what information is included (best-fit values, uncertainties, and correlations). It distinguishes from siblings like 'list_experimental_data' (which likely lists datasets) and 'fetch_hepdata_record' (which might fetch raw data), but doesn't explicitly name alternatives.

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

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

The description implies usage when detailed dataset information is needed, but doesn't explicitly state when to use this tool versus alternatives like 'fetch_hepdata_record' or 'get_latest_higgs_data'. It provides some context by specifying 'experimental dataset', but lacks clear exclusions or named alternatives.

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 lacks critical behavioral details. It mentions fetching 'latest' data but doesn't define what 'latest' means (e.g., most recent publication, update timestamp). It doesn't disclose rate limits, authentication needs, data freshness guarantees, or potential data volume/format. The description adds minimal context beyond the basic fetch operation.

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 efficiently structured in two sentences: first states the action and sources, second specifies the return content. It's appropriately sized for the tool's complexity, though could potentially be more front-loaded by integrating return details into the first sentence.

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

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

For a data-fetching tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It lacks behavioral transparency (rate limits, auth, freshness), doesn't explain the relationship between parameters, and provides no output format details. The description should compensate for missing structured data but doesn't adequately do so.

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%, providing clear parameter documentation. The description adds no parameter-specific semantics beyond what's in the schema (e.g., doesn't explain how 'channel' interacts with 'collaboration', or default behavior when parameters are omitted). Baseline 3 is appropriate since the 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 clearly states the action ('Fetch'), resources ('Higgs boson measurement data from both HEPData and CERN Open Data portals'), and output content ('signal strength measurements, coupling measurements, and analysis results'). It distinguishes from siblings like 'fetch_hepdata_record' and 'get_cern_opendata_record' by specifying it fetches from both sources and focuses on latest Higgs data, but doesn't explicitly contrast with 'search_hepdata' or 'search_cern_opendata'.

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 'fetch_hepdata_record', 'get_cern_opendata_record', 'search_hepdata', or 'search_cern_opendata'. It mentions fetching from both portals but doesn't clarify if this is for consolidated latest data versus specific searches or individual portal access.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool's function but does not cover critical aspects like whether it's read-only, requires authentication, has rate limits, or what the output format entails (e.g., numerical values, plots, or errors). This leaves significant gaps in understanding how the tool behaves beyond its basic purpose.

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, efficient sentence that front-loads the core purpose without unnecessary details. Every word contributes directly to explaining what the tool does, making it highly concise and well-structured for quick understanding.

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 moderate complexity (2 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the purpose and parameters indirectly via the schema, but lacks details on output behavior, error handling, or integration with sibling tools. This results in a minimal viable description that meets basic needs but leaves room for improvement in contextual richness.

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, clearly documenting both parameters ('mass' and 'sqrts') with units and enum values. The description adds minimal value beyond the schema by mentioning 'specified mass and energy', but does not provide additional context like typical mass ranges or energy implications. With high schema coverage, 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?

The description clearly states the action ('Get') and resource ('Standard Model predictions for Higgs cross sections and branching ratios'), specifying the scientific context. However, it does not explicitly differentiate from sibling tools like 'get_latest_higgs_data' or 'compute_sm_likelihood', which might offer related Higgs data or computations, leaving some ambiguity in tool selection.

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 'get_latest_higgs_data' for experimental data or 'compute_sm_likelihood' for likelihood calculations. It lacks explicit context, prerequisites, or exclusions, relying solely on the implied need for Standard Model predictions at specific parameters.

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 mentions retrieving version information but doesn't specify whether this is a read-only operation, if it requires authentication, what the output format is, or any rate limits. For a tool with zero annotation coverage, this leaves significant gaps in understanding its 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?

The description is a single, clear sentence with no wasted words. It front-loads the key action ('Get version information') and specifies the target resources efficiently, making it easy to parse and understand quickly.

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 output schema), the description is adequate but minimal. It covers the basic purpose but lacks details on usage context, behavioral traits, or output format, which could be helpful for an AI agent to use it correctly in a broader workflow.

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, and the input schema has 100% description coverage (though empty). The description doesn't need to add parameter details, so it meets the baseline expectation. A score of 5 would require extra value, such as explaining why no parameters are needed, which is not present here.

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 'Get' and the resource 'version information for Lilith library and experimental database', making the purpose specific and understandable. However, it doesn't explicitly differentiate this tool from its siblings (e.g., 'get_dataset_info' or 'get_latest_higgs_data'), which would require 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?

The description provides no guidance on when to use this tool versus alternatives like 'get_dataset_info' or 'update_database', nor does it mention any prerequisites or context for usage. It only states what the tool does, not when it should be invoked.

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 mentions listing files for download, which implies a read-only operation, but does not address potential behaviors like pagination, rate limits, authentication needs, or error handling. This leaves significant gaps in understanding how the tool behaves beyond its basic function.

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

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

The description is a single, clear sentence that efficiently conveys the tool's purpose without unnecessary words. It is front-loaded and every part earns its place, making it highly concise and well-structured for quick comprehension.

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 moderate complexity (2 parameters, no output schema, no annotations), the description is adequate but incomplete. It covers the basic purpose but lacks details on behavioral aspects and usage context relative to siblings. Without annotations or output schema, more guidance on what to expect from the tool would improve completeness.

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 the parameters (recid and filterPattern). The description adds no additional semantic details about the parameters, such as examples or constraints beyond what the schema provides. This meets the baseline for high schema coverage but does not enhance parameter understanding.

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 ('List files available for download') and the resource ('from a specific CERN Open Data record'), making the purpose immediately understandable. However, it does not explicitly differentiate from sibling tools like 'get_cern_opendata_record' or 'search_cern_opendata', which might have overlapping functionality, so it falls short of a perfect score.

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 minimal guidance by specifying the context ('from a specific CERN Open Data record'), but it does not indicate when to use this tool versus alternatives such as 'search_cern_opendata' or 'get_cern_opendata_record'. There are no explicit when/when-not instructions or named alternatives, leaving usage unclear relative to 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 are provided, so the description carries the full burden of behavioral disclosure. It states the tool lists datasets but doesn't describe output format (e.g., list, table, JSON), pagination, rate limits, or authentication requirements. For a tool with no annotations, this leaves significant gaps in understanding how the tool behaves beyond its basic function.

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, efficient sentence that front-loads the core purpose ('List available experimental datasets') and adds organizational context ('organized by experiment and run period'). There is no wasted text, and it's appropriately sized for a simple listing tool with two parameters.

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 low complexity (2 parameters, no output schema, no annotations), the description is minimally adequate. It covers the purpose but lacks behavioral details like output format or usage context. Without annotations or output schema, the description should do more to compensate, but it falls short, resulting in a mediocre completeness score.

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 both parameters ('experiment' and 'runPeriod') fully documented in the schema, including enums and descriptions. The description adds no additional parameter semantics beyond implying filtering by experiment and run period, which is already covered in the schema. This meets the baseline of 3 for high schema coverage without extra value from the 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 clearly states the verb ('List') and resource ('available experimental datasets in the Lilith database'), specifying organization by experiment and run period. It distinguishes from siblings like 'get_dataset_info' or 'search_hepdata' by focusing on listing datasets rather than retrieving detailed info or searching. However, it doesn't explicitly differentiate from 'list_cern_opendata_files', which might overlap in purpose but targets different data sources.

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. It doesn't mention prerequisites, such as needing database access, or compare to siblings like 'get_dataset_info' for detailed metadata or 'search_ern_opendata' for broader searches. The lack of explicit when/when-not statements leaves the agent to infer usage from the tool 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the tool performs a scan and returns a profile, but doesn't describe computational characteristics (e.g., execution time, resource usage), error handling, or what 'likelihood profile' entails structurally. This is inadequate for a tool with mathematical/statistical operations.

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, efficient sentence that directly states the tool's function without unnecessary words. It's appropriately sized for a straightforward scanning operation.

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 mathematical scanning tool with no annotations, no output schema, and incomplete parameter documentation, the description is insufficient. It doesn't explain what a 'likelihood profile' contains, how results are formatted, or any computational constraints. The context signals indicate significant gaps in documentation.

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 50% (only 'fixedParams' has a description). The tool description adds no parameter-specific information beyond what's in the schema. It doesn't explain what 'param' object represents or how 'fixedParams' should be structured. Baseline 3 is appropriate given the partial schema 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 action ('Perform a 1D parameter scan') and the outcome ('return likelihood profile'), which distinguishes it from general analysis tools. However, it doesn't explicitly differentiate from its sibling 'scan_2d' beyond the dimensionality implied in the name.

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 'scan_2d', 'compute_likelihood', or other analysis tools. The description lacks context about appropriate scenarios or prerequisites for a 1D scan.

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 offers limited behavioral insight. It mentions the tool returns likelihood values but doesn't disclose computational characteristics (e.g., execution time, resource intensity), error handling, or whether it's read-only versus mutative. The example 'CV-CF plane' hints at physics applications but lacks operational 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 a single, efficient sentence that front-loads the core purpose. It avoids redundancy and wastes no words, 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?

For a tool with 3 parameters, low schema coverage (33%), no annotations, no output schema, and nested objects, the description is insufficient. It doesn't explain the output format (e.g., array structure for contour data), error conditions, or how the scan relates to sibling tools, leaving the agent with significant uncertainty.

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 low at 33%, with only 'param1.name' and 'fixedParams' having descriptions. The description adds minimal value beyond the schema, mentioning 'CV-CF plane' as an example for parameter names but not explaining the semantics of min/max/steps or how 'fixedParams' should be structured. It partially compensates but leaves significant gaps.

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 performs a '2D parameter scan' and returns 'likelihood values for contour plotting', which is specific about the action and output. It distinguishes from sibling tools like 'scan_1d' by specifying 2D scanning, but doesn't explicitly differentiate from other likelihood-related tools like 'compute_likelihood'.

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 minimal guidance, only implying usage for contour plotting. It doesn't specify when to use this tool versus alternatives like 'scan_1d' for 1D scans or 'compute_likelihood' for single-point calculations, nor does it mention 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?

With no annotations provided, the description carries full burden but offers minimal behavioral insight. It mentions the portal scope and content types but doesn't disclose whether this is a read-only operation, how results are returned (e.g., pagination, format), rate limits, authentication needs, or error conditions. For a search tool with zero annotation coverage, this leaves 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, efficient sentence that front-loads the core purpose without unnecessary words. Every element ('Search', 'CERN Open Data portal', 'Higgs-related datasets, analysis code, and documentation') contributes directly to understanding the tool's function.

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 search tool with 3 parameters, no annotations, and no output schema, the description is incomplete. It lacks details on behavioral traits (e.g., result format, limitations), usage context relative to siblings, and output expectations. While concise, it doesn't compensate for the missing structured information, leaving the agent with insufficient guidance.

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%, providing full parameter documentation. The description adds marginal value by implying the search focuses on Higgs-related content (which relates to the default 'query' value) and listing content types that map to the 'type' enum. However, it doesn't provide additional context beyond what the schema already specifies, meeting the baseline for high 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 action ('Search') and target ('CERN Open Data portal') with specific content focus ('Higgs-related datasets, analysis code, and documentation'). It distinguishes from most siblings like 'analyze_2hdm' or 'compute_likelihood' by being a search tool, though it doesn't explicitly differentiate from 'search_hepdata' or 'get_cern_opendata_record' which have related but distinct purposes.

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

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

No guidance is provided on when to use this tool versus alternatives. It doesn't mention when to prefer 'search_hepdata' (which searches HEPData) or 'get_cern_opendata_record' (which retrieves specific records), nor does it specify prerequisites or typical use cases beyond the general search 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 but discloses minimal behavioral traits. It mentions 'search' and 'new Higgs measurement data', implying read-only retrieval, but doesn't cover aspects like rate limits, authentication needs, pagination, result format, or error handling. This is inadequate for a search tool with 5 parameters.

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, efficient sentence with zero waste—it directly states the tool's purpose without redundancy. It's appropriately sized and front-loaded, making it easy to parse.

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 (5 parameters, no annotations, no output schema), the description is incomplete. It lacks behavioral context (e.g., how results are returned, error cases), doesn't explain the relationship between parameters (e.g., if 'query' overrides others), and provides no output details, leaving significant gaps for agent 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 all 5 parameters thoroughly. The description adds no additional parameter semantics beyond implying Higgs-specific filtering, which is partially covered by the schema's enum/descriptions. Baseline 3 is appropriate as the 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 clearly states the verb ('search') and resource ('HEPData repository'), specifying the target data ('new Higgs measurement data from ATLAS and CMS'). It distinguishes from some siblings like 'fetch_hepdata_record' (retrieves specific records) or 'list_experimental_data' (lists without filtering), but doesn't explicitly differentiate from 'search_cern_opendata' (which searches different 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?

No explicit guidance on when to use this tool versus alternatives like 'search_cern_opendata' (for CERN Open Data) or 'get_latest_higgs_data' (which might retrieve pre-curated data). The description implies usage for Higgs data searches, but lacks context on prerequisites, exclusions, or comparative 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions that the tool can 'check for and optionally download' data, implying both read and write operations, but doesn't detail permissions required, whether downloads are destructive or additive, rate limits, or error handling. For a tool that updates a database, this lack of behavioral context is a significant gap.

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, efficient sentence that front-loads the core functionality. It avoids redundancy and wastes no words, making it easy to parse. However, it could be slightly more structured by separating the check and download aspects, but this is minor.

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 (updating a database with optional downloads) and lack of annotations and output schema, the description is insufficient. It doesn't cover what happens on success/failure, the format of updates, or how it interacts with the local database. For a mutation tool with no structured safety or output info, more completeness is needed.

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 all three parameters thoroughly. The description adds no additional meaning beyond what's in the schema—it doesn't explain parameter interactions, default behaviors, or usage examples. With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.

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: 'Check for and optionally download new experimental data from HEPData to update the local Lilith database.' It specifies the verb ('check for and optionally download'), resource ('new experimental data'), and target ('local Lilith database'). However, it doesn't explicitly differentiate from sibling tools like 'fetch_hepdata_record' or 'get_latest_higgs_data', which prevents a score of 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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'fetch_hepdata_record' or 'search_hepdata', nor does it specify prerequisites, exclusions, or contextual triggers for usage. This leaves the agent without clear direction on 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?

With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does (validation) but doesn't describe what happens on success/failure, error formats, whether it's read-only (implied but not stated), performance characteristics, or authentication needs. For a validation tool with zero annotation coverage, this leaves significant behavioral 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, efficient sentence that communicates the essential purpose without any wasted words. It's appropriately sized for a simple validation tool and front-loads the key 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 single-parameter validation tool with no output schema and no annotations, the description adequately covers the basic purpose but lacks information about return values, error conditions, and behavioral details. It's minimally viable but has clear gaps in completeness given the 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?

Schema description coverage is 100%, so the schema already documents the single 'xml' parameter completely. The description adds no additional parameter semantics beyond what's in the schema. Baseline 3 is appropriate when the schema does all the parameter documentation work.

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 ('validate'), the resource ('XML input format for Lilith'), and distinguishes it from alternatives by specifying 'without running the full calculation.' This differentiates it from sibling tools like compute_likelihood or scan_1d that perform calculations.

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: when you need to check XML format validity before proceeding with calculations. It implies an alternative (running the full calculation) but doesn't explicitly name when NOT to use it or list specific sibling alternatives for validation.

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