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

Annotations indicate readOnlyHint=false and destructiveHint=false, implying a safe write operation. However, the description adds the vague 'may create or update' without clarifying the exact behavior, authorization needs, or side effects. Beyond the annotations, the description offers minimal transparency.

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

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

The description is too short to be effective; it omits essential context. The second sentence 'This may create or update Monarch data' adds confusion rather than value. A more structured, front-loaded description would better serve the agent.

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 (9 parameters, no output schema, low schema coverage), the description is vastly incomplete. It leaves the agent without understanding return values, required parameter relationships, or the difference between creation and update scenarios. The description fails to compensate for missing structured information.

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 schema description coverage at only 22%, the description fails to explain the purpose or constraints of most parameters. It does not describe any parameter semantics beyond what is in the schema. The agent likely cannot infer correct usage for parameters like 'fields', 'balance', 'owner_user_id' etc.

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

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

The description states 'Create manual account' which identifies the action and resource, but the additional phrase 'This may create or update Monarch data' introduces ambiguity about whether this tool can also update existing accounts, which conflicts with the sibling tool 'accounts_update_account'. The purpose is partially clear but lacks precision.

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 usage guidance is provided. The description does not specify when to use this tool versus alternatives like 'accounts_update_account', nor does it explain prerequisites or consequences. The agent receives no context for 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?

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false. The description adds 'This may delete, clear, reset, or otherwise remove data,' which elaborates on the destructive nature but doesn't provide substantial new behavioral insight beyond the annotations.

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

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

The description is very short (two sentences). However, the second sentence is somewhat redundant given the first. Still, it is concise and front-loaded with the core action.

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

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

No output schema exists, yet the description doesn't specify what happens after deletion (e.g., return value, side effects, or impact on related data). For a destructive tool, more information about consequences 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 50% (fields and output_mode have descriptions), but the tool description doesn't mention any parameters. It fails to add value for the required account_id parameter or session_path, leaving the agent without guidance on their meaning or usage.

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 'Delete account', which is a specific verb-resource pair. This distinguishes it from sibling tools like accounts_update_account or accounts_get_account, which have different actions.

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

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

No guidance on when to use this tool vs alternatives (e.g., deactivating vs deleting). No prerequisites or conditions are mentioned, leaving the AI agent without context for appropriate invocation.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no behavioral context beyond these, such as what data is returned or any side effects.

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

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

The description is extremely concise at two words, but this brevity sacrifices informativeness. It is appropriately sized for a simple tool but lacks essential details.

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

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

The description is incomplete for a tool with 4 parameters, especially with no output schema. It does not cover return values, parameter relationships, or usage examples, leaving significant gaps despite available annotations.

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% (fields and output_mode have descriptions, but account_id and session_path do not). The description does not explain any parameters, missing an opportunity to compensate for the schema 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 states 'Get account,' which clearly indicates the action and resource. However, it does not differentiate from sibling tools like accounts_get_account_history or accounts_get_historical_balances, which also retrieve account-related 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 guidance is provided on when or when not to use this tool compared to alternatives. There is no mention of prerequisites, context, 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?

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description adds no behavioral context. It does not disclose what data is returned, whether pagination occurs, or any other behavioral trait beyond what annotations already provide.

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 short (four words) but this is under-specification, not conciseness. Key details like return shape, parameter roles, and usage context are missing, making it minimally useful.

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

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

With no output schema and four parameters, the description provides no information about what the tool returns (e.g., list of transactions, balance summaries, or raw data). It is inadequate for an agent to correctly understand the tool's function and output.

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

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

Schema description coverage is 50%, with account_id and session_path lacking descriptions. The description does not explain these parameters or clarify how they affect the 'history' output, failing to compensate for the schema's 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 'Get account history' is almost a tautology, simply restating the name and title. It does not distinguish this tool from siblings like accounts_get_historical_balances or accounts_get_account, leaving ambiguity about what 'history' entails (e.g., transactions, balance changes).

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

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

No guidance on when to use this tool versus alternatives. With siblings covering specific account data, historical balances, and net worth, the lack of usage context forces the agent to guess.

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

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

The description adds no behavioral insights beyond the annotations (readOnlyHint, openWorldHint, idempotentHint). It fails to disclose details such as that it returns balances for specified accounts at a single date, or any constraints like the maximum date range. No contradiction with annotations.

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

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

The one-sentence description is overly terse, bordering on useless. It lacks structure and essential detail, achieving brevity at the expense of clarity.

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

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

Given the tool has 5 parameters, no output schema, and operates within a complex domain (account balances), the description is critically incomplete. It omits what data is returned, how filtering works, and the meaning of 'historical'.

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 only 40% of parameters having descriptions in the schema, the tool description must compensate but does not. It offers no additional meaning for parameters like 'filters' or 'balance_date', leaving the agent to infer from names alone.

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 'Get historical balances' is a tautology of the tool name and title. It fails to specify that it retrieves account balances at a past date, nor does it distinguish from sibling tools like accounts_get_account_history or accounts_get_net_worth_breakdown which also deal with historical financial 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 guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, scenarios, or exclusions, leaving the agent without context for correct 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as false. The description adds no additional behavioral context, but does not contradict annotations. With annotations present, the bar is lower; however, the description does not provide extra useful behavioral details.

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

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

At 4 words, the description is extremely minimal but fails to provide necessary information. It is under-specified for a tool with 6 parameters and no output schema, making it inefficient rather than concise.

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

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

The description is too brief to be complete. Given the tool's complexity (6 parameters, no output schema), it does not explain what the net worth breakdown contains, how filters work, or what output format to expect. The description leaves 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 only 33% (2 out of 6 parameters have descriptions). The description 'Get net worth breakdown' adds no meaning to parameters like filters, start_date, timeframe, or session_path. With low coverage, the description must compensate, but it does not.

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 'Get net worth breakdown' clearly identifies the action (get) and resource (net worth breakdown), but lacks specificity about what the breakdown includes. It does not distinguish it from the sibling tool 'accounts_get_net_worth_performance'.

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 accounts_get_net_worth_performance or other tools. There is no context on prerequisites or typical use cases.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is clear. The description adds no additional behavioral context such as how performance is calculated or what data is aggregated, but it does not contradict annotations. With annotations covering safety, a mid-range score is appropriate.

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 (one sentence), but this is not a virtue when it sacrifices clarity and completeness. It lacks structure and front-loading of 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?

With 7 parameters, no output schema, and a complex financial metric, the description is woefully incomplete. It does not explain what 'performance' means, what the tool returns, or how filters and date ranges affect the output.

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

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

Schema description coverage is 29%, meaning most parameters lack description. The tool description does not explain any parameters or their roles. For example, start_date, end_date, and filters are not mentioned, so the description adds no value beyond the schema for 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 'Get net worth performance' provides a verb and resource, but 'performance' is vague and does not distinguish clearly from sibling tools like accounts_get_net_worth_breakdown or accounts_get_historical_balances. It lacks specificity on whether it returns returns, growth rates, or other metrics.

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 given on when to use this tool versus alternatives. The description does not mention filtering by accounts, date ranges, or any context that would help the agent decide when to invoke it.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is clear. However, the description does not add any behavioral context beyond that, such as mention of pagination, filtering capabilities, or the output_mode parameter which controls data shape.

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 (two words), which is acceptable for a simple operation but lacks structure. Given the presence of multiple parameters and options, a few more sentences would improve clarity without being verbose.

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

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

The tool has 4 parameters including optional filters and output modes, yet the description provides no context on how to use these or what the result looks like. No output schema exists, so the description should compensate, but it does not.

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% (fields and output_mode have descriptions; filters and session_path do not). The description 'List accounts' adds no explanation of any parameter, leaving the agent to rely solely on the schema without additional context.

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

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

The description clearly states the tool lists accounts, which is a specific verb+resource. However, it lacks any details about scope (e.g., all accounts, filtered accounts) and does not distinguish from sibling tools like accounts_get_account, though no sibling directly conflicts.

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

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

No guidance is provided on when to use this tool versus alternatives such as accounts_get_account for a single account or other list tools. The description is too brief to convey appropriate usage context.

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

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

The description notes that the tool 'may create or update Monarch data', hinting at non-destructive but potentially creative behavior. However, it does not specify conditions under which creation occurs or other side effects. Annotations are sparse, so the description adds some value but is insufficiently detailed.

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

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

The description is very concise, just one sentence. While brevity is good, it omits essential info. It is not overly verbose, but it's under-specified for 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?

Given 13 parameters, no output schema, and limited annotations, the description is severely lacking. It fails to explain what fields can be updated, return value, or constraints. It is not complete enough for effective tool selection and invocation.

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

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

Schema description coverage is only 15% (only 'fields' has a description). The tool description does not explain any parameters, leaving agents to rely solely on parameter names and types, which may be ambiguous. It adds minimal value beyond the schema.

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

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

The description clearly states 'Update account', which identifies both the verb and the resource. It is straightforward and matches the tool's name and title, though it does not differentiate from sibling tools like create or delete.

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

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

No guidance on when to use this tool versus alternatives (e.g., accounts_create_manual_account). There is no mention of prerequisites or scenarios where this tool is appropriate or not.

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

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

The description adds only 'This may create or update Monarch data,' which is already implied by readOnlyHint=false annotations. No additional behavioral traits (e.g., session management, token handling) are disclosed.

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

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

The description is a single sentence with no fluff, but it is too vague for a tool with 8 parameters and authentication semantics. Conciseness comes at the cost of completeness.

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

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

The description fails to cover the authentication flow, return behavior, or the function of critical parameters. For a tool with no output schema and high parameter count, this is severely incomplete.

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 only 25% schema description coverage, the description does not explain the purpose of key parameters like email, password, mfa_code, or session_path. The agent must rely on parameter names alone.

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

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

The description states 'Create session' with a clear verb and resource. However, it does not differentiate from sibling tools like auth_load_session and auth_save_session, which could confuse the agent on which tool to use.

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, nor any prerequisites or authentication flow context. The agent is left to infer usage from the name alone.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear. The description adds no additional behavioral context beyond what annotations provide, thus offering no extra value.

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 at two words, but it is under-informative. It sacrifices necessary detail for brevity, making it less useful for an agent.

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

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

With 4 parameters, no output schema, and only 50% schema coverage, the description is highly incomplete. It does not cover return values, behavior, or any context needed to 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 description does not explain any parameters. Schema coverage is only 50%, with undocumented parameters like 'path' and 'include_token'. The description fails to compensate for the missing 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 'Load session' states the verb 'load' and resource 'session', so the basic purpose is clear. However, it does not differentiate from sibling tools like auth_create_session or auth_save_session, which could also involve session management.

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

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

No guidance on when to use this tool versus alternatives. No context about prerequisites or typical use cases 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?

The description adds that the tool 'may create or update' data, which is consistent with annotations (readOnlyHint=false). However, it does not disclose potential side effects, permission requirements, error conditions, or the nature of the update. Minimal value beyond annotations.

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

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

The description is very short (two sentences) and front-loaded, but it sacrifices clarity for brevity. It is concise but not sufficiently informative, earning a middle score.

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 lack of an output schema, the presence of sibling tools, and four parameters, the description is grossly inadequate. It does not explain the tool's role in authentication, how to use the 'path' or 'session' parameters, or what the return value looks like. The agent cannot effectively invoke this tool based on this description alone.

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 description provides no parameter-level information. With 50% schema description coverage, the description should compensate but doesn't explain what 'path' or the 'session' object fields represent. The agent must rely solely on the schema, which lacks descriptions for critical parameters.

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

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

The description says 'Save session' which identifies a specific verb and resource, but fails to clarify what a session is in this context or how it differs from sibling tools like auth_create_session and auth_load_session. The mention of 'Monarch data' is confusing and doesn't align with the auth prefix.

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

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

No guidance on when to use this tool versus auth_create_session or auth_load_session. The description provides no context for appropriate usage scenarios or prerequisites, leaving the agent without decision support.

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

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

The description aligns with annotations (destructiveHint=true) by mentioning potential data removal. However, it adds minimal context beyond what annotations already indicate, and the openWorldHint is not explained.

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 very brief (one sentence) and gets to the point. However, the brevity sacrifices necessary detail.

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

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

With 5 parameters, no output schema, and a destructive action, the description is insufficient. It doesn't explain the meaning of 'confirm', what fields do, or the implications of openWorldHint=true.

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 40% (2 of 5 parameters have descriptions). The tool description does not explain any parameters or their roles, leaving agents to rely on the schema alone, which is incomplete.

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

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

The description states the action (clear) and resource (budget), but fails to distinguish from sibling tools like budget_reset_budget. The wording 'may delete, clear, reset, or otherwise remove data' is vague and does not clarify what clearing a budget entails compared to 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?

No guidance on when to use this tool versus alternatives (e.g., budget_reset_budget, budget_delete_budget). No context about prerequisites or when not to use it.

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

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

The description says 'may create or update Monarch data,' but this is vague. Annotations indicate non-read-only and non-destructive, but the description does not disclose important behavioral traits such as idempotency, side effects (e.g., overwriting existing budget), permissions required, or whether it triggers downstream effects like rollovers. The 'openWorldHint' true suggests additional side effects, but these are not explained.

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

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

The description is a single sentence, which is concise, but it sacrifices clarity. It could be restructured to include key information without increasing length significantly. The title 'Budget Create Budget' is redundant.

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

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

Given the tool has 4 parameters (1 required), no output schema, and many sibling tools, the description is insufficient. It does not explain what a budget is, the creation process, return values, or error conditions. The user cannot determine whether the tool is appropriate without additional 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 schema description coverage is 50% (fields and output_mode have descriptions, month and session_path do not). The description adds no parameter-specific meaning; it only says 'Create budget.' The 'month' parameter is essential but only has a title 'Month' with no format or constraints explained. The 'session_path' parameter is completely undocumented.

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

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

The description states 'Create budget' which identifies the action, and the required 'month' parameter suggests creating a budget for a specific month. However, it does not clarify if this creates a new budget record or updates an existing one, and it fails to distinguish from sibling tools like 'budget_set_budget_amount' or 'budget_get_budget'. The phrase 'may create or update Monarch data' adds ambiguity.

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. The sibling tools include many budget-related actions (set amounts, get budget, reset budget, etc.), but the description does not specify scenarios or prerequisites. For example, it does not clarify whether creating a budget requires a month to exist or what happens if it already exists.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds no extra behavioral information, such as what budget data is returned or how it interacts with budgets. It provides minimal added value.

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 short but not concise in a helpful way. It lacks structure and front-loading of key information. The single word 'budget' could be more meaningful if expanded.

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

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

Given the tool has 4 parameters, no output schema, and siblings with similar names, the description is incomplete. It does not specify what the tool returns, how to use the month parameter, or any important notes. For a simple get operation, more context 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?

The input schema has 4 parameters with 50% description coverage (fields and output_mode have descriptions, but month, which is required, lacks a description in both schema and tool description). The description does not explain any parameter meanings, so it fails to compensate for the schema's 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 'Get budget' is a tautology that merely restates the tool name. It does not specify what kind of budget data is retrieved or distinguish it from sibling tools like budget_get_budget_category or budget_get_budget_settings.

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

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

No guidance is provided on when to use this tool versus alternatives such as budget_list_budget_months or budget_get_budget_category. The description lacks any context regarding prerequisites or appropriate 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?

Annotations declare readOnlyHint, idempotentHint, and destructiveHint=false, which the description does not contradict. The description adds no behavioral context beyond what annotations provide, such as error handling or output format, but it is not misleading.

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 brief (two words), but fails to include essential details. Conciseness should be efficient, not sparse; this is under-specified rather than optimally concise.

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

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

Given the absence of an output schema and the moderate parameter count (5, with 2 required), the description should provide more context about return values and parameter usage. The current description leaves significant gaps for the agent to fill.

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 40% coverage (fields and output_mode have descriptions), but the description adds nothing about the required parameters month and category_id. The lack of explanation for these fields means the agent must infer their formats or constraints.

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 'Get budget category' is minimal but conveys a specific verb and resource. However, it does not differentiate this tool from siblings like budget_get_budget or categories_get_category, leaving ambiguity about what a 'budget category' is in this context.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites or exclusions, leaving the agent to infer usage from the name alone.

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

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

Annotations provide strong safety guarantees (readOnlyHint, idempotentHint, destructiveHint). The description does not add behavioral context such as rate limits, authorization needs, or side effects. With annotations covering the safety profile, a score of 3 is appropriate as it adds minimal value beyond annotations.

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

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

The description is extremely concise (three words), but it lacks structure. While it is front-loaded, it does not earn its place by providing enough information; it essentially restates the tool name. A single sentence without details is not optimally structured for agent use.

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 three parameters, strong annotations, and no output schema, the description is too brief. It does not explain what settings are returned, how to interpret results, or how to use parameters like 'output_mode' and 'fields'. The description leaves significant gaps for an agent to infer behavior.

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 67% (two out of three parameters have descriptions). The tool description does not enhance parameter understanding; it does not explain what 'budget settings' encompasses or how parameters like 'session_path' affect behavior. The description fails to compensate for the undocumented parameter.

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

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

The description 'Get budget settings' clearly states the verb and resource. It distinguishes from sibling tools like 'budget_get_budget' (which gets a specific budget) and 'budget_get_budget_category' by focusing on the overarching settings. The input schema further supports this with parameters for field selection and output mode.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention preconditions or exclusions. There is no context about when this tool is appropriate or when to prefer related tools like 'budget_get_budget_settings' over others.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description 'Get' aligns with these annotations. No additional behavioral details are provided, but no contradictions either.

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

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

The description is a single concise sentence of 5 words. It is front-loaded and efficient, but borderlines on under-specification for agents.

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

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

Despite having good annotations, the description lacks context about what flex rollover settings are, what fields are returned, or how the output_mode parameter affects results. For a simple getter, 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 coverage is 67% (2 of 3 parameters described). The description adds no information about parameters beyond what the schema already provides. Baseline 3 is appropriate as the schema handles most of the 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 it retrieves flex rollover settings. It is specific and distinguishes from sibling 'budget_set_flex_rollover_settings' by implying a read operation. However, it could be more explicit about the scope.

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

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

No guidance on when to use this tool versus alternatives like budget_get_budget_settings or budget_set_flex_rollover_settings. No context provided for prerequisites or typical use cases.

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

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) provide a safety profile, reducing the need for behavioral details. The description adds nothing beyond these annotations, but also does not contradict them. For a read-only tool, this is minimally adequate.

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?

Extremely concise but at the expense of completeness. Four words do not provide enough context for a tool with 5 parameters. The description is under-specified, not efficiently concise.

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

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

The tool has 5 parameters, 2 required, and no output schema. The description does not explain what the return data looks like, how the months are filtered, or any edge cases. An agent would be uncertain about the output format and behavior without additional 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 40%, leaving start_month and end_month undocumented. The tool description does not mention parameters or compensate for missing schema descriptions. The agent must infer usage from parameter names alone, which is insufficient for complex date formatting.

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 budget months.' It is a verb+resource pattern. However, it does not differentiate from sibling list tools or specify what constitutes a 'budget month' (e.g., months with budget data vs all months in a range).

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 usage guidelines provided. The description does not indicate when to use this tool vs other budget tools or how to set the date range behavior. The agent receives no contextual cues about prerequisites or 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?

While annotations already declare destructiveHint=true, the description adds only vague language ('may delete, clear, reset, or otherwise remove data') without specifying what data is affected (e.g., budget amounts, categories, rollover settings) or the scope (single month? all categories?).

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 short sentences, but the first is redundant with the name and the second is vague. Lacks front-loading of critical information such as required parameters or effect.

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 destructive tool with 8 parameters and no output schema, the description fails to explain the tool's effect, required inputs, or how optional parameters influence behavior. Completely inadequate for reliable agent invocation.

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

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

Schema coverage is only 25% (2 of 8 parameters have descriptions). The description provides no parameter information, leaving agents without guidance on the required 'month' parameter or optional ones like 'overwrite_existing'.

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 'Reset budget' is almost tautological with the tool name. It does not differentiate from sibling 'budget_clear_budget', and the vague elaboration adds no specificity about what exactly is reset or how it differs from similar operations.

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

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

No guidance on when to use this tool versus alternatives like budget_clear_budget or budget_create_budget. No context about prerequisites (e.g., budget existence) 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?

Annotations already indicate destructiveHint=true, and the description echoes this with 'may delete, clear, reset, or otherwise remove data'. However, it lacks specificity about what exactly is removed, which rollovers are affected, and whether parameters like category_id scope the action.

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

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

The description is brief (two short sentences), but the second sentence is redundant and vague. It is front-loaded but could be more informative without increasing length.

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 7 parameters, no output schema, and destructive nature, the description fails to provide sufficient context. It does not explain how parameters interact, what returns are expected, or how this differs from sibling tools.

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 description adds no value to the input schema. With only 29% schema description coverage, the required parameter 'month' and key parameters like 'category_id' have no explanation in the description. The tool's core behavior is left vague.

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

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

The description states 'Reset budget rollover', clearly indicating the action and resource. It differentiates from siblings like 'budget_reset_budget' which resets the entire budget, but does not elaborate on what exactly 'reset' means, leaving some ambiguity.

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 'budget_set_budget_rollover' or 'budget_reset_budget'. The description implies use for resetting rollovers but does not provide usage context 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?

Annotations already indicate readOnlyHint=false, so the description's statement 'may create or update' adds no new behavioral insight. No additional effects (e.g., idempotency, side effects on existing budgets) are disclosed beyond the annotations.

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

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

The description is very short (two sentences), which is concise, but it is overly minimal given the tool's complexity. It lacks substance needed for effective agent usage, so while brief, it is not appropriately informative.

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

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

Given the high parameter count, low schema coverage, absence of output schema, and many sibling tools, the description is severely incomplete. It does not cover return values, parameter details, or usage context, leaving the agent with insufficient information.

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 schema description coverage at only 25%, the description does not compensate by explaining any of the 8 parameters. It provides no meaning beyond the bare schema names, which is insufficient for an agent to correctly set parameters like 'fields', 'session_path', or 'apply_to_future'.

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

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

The description states the verb 'Set budget amount' which matches the tool name and title, but it fails to differentiate from sibling tools like budget_set_budget_group_amount. The phrase 'create or update Monarch data' adds minimal context and does not specify which budget entity is being set (e.g., monthly category budget).

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

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

No guidance is provided on when to use this tool versus alternatives such as budget_set_budget_group_amount or budget_create_budget. The description lacks any context for selection, leaving the agent without 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?

Annotations already indicate it's not read-only (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds that it 'may create or update Monarch data,' which confirms the mutation behavior. This adds some value beyond annotations but doesn't disclose specific side effects or authorization needs.

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 vague sentence. While concise, it lacks important details and is not well-structured (no bullet points, no parameter breakdown).

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

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

Given the high parameter count (11), no output schema, and minimal description, the tool definition is severely incomplete. It does not explain what rollover does, how parameters interact, or what the result looks like.

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 11 parameters and only 18% schema description coverage, the description provides no explanation of any parameters. It fails to add meaning beyond the input schema, leaving the agent to infer parameter semantics from names alone.

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

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

The description clearly states that the tool sets budget category rollover and may create or update data. It distinguishes itself from sibling tools like budget_set_budget_group_rollover by focusing on category-level rollover, but it doesn't define 'rollover' itself.

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

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

There is no guidance on when to use this tool versus alternatives (e.g., budget_reset_budget_rollover, budget_set_budget_group_rollover). No context about prerequisites or typical use cases 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?

The description 'This may create or update Monarch data' adds minimal behavioral context beyond the annotations (readOnlyHint=false). Annotations already indicate it is a write operation but not destructive. The description does not reveal further traits like idempotency 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?

The description is highly concise, using two sentences to state purpose and a behavioral note. No extraneous words, and the key information is front-loaded.

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

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

Given the tool has 5 parameters, no output schema, and no nested objects, the description is insufficient. It fails to explain the variability option, required category, or return behavior, leaving the agent underinformed for correct invocation.

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

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

With only 40% schema description coverage, the description should explain parameters but does not. It does not mention category_id, variability enum, or other parameters, leaving the agent to infer meaning solely from the schema, which lacks descriptions for critical fields.

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 sets budget category variability, which is a specific verb-resource pair. It distinguishes from similar sibling tools like budget_set_budget_group_variability by the resource type, but does not explicitly mention this 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 no guidance on when to use this tool versus alternative sibling tools like budget_set_budget_amount or budget_set_budget_category_rollover. There is no mention of prerequisites or context.

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

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

Annotations already signal mutation (readOnlyHint=false) but are not destructive. The description adds 'may create or update', which is redundant and doesn't disclose specific side effects, permission requirements, or rate limits.

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 very short (two sentences), but it is appropriately concise. However, it lacks substance; it could be more informative without adding length.

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

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

With no output schema and 8 parameters (3 required), the description should explain the purpose and usage more thoroughly. It does not define what a budget group is or what the parameters mean, making it incomplete.

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 only 25% (fields and output_mode have descriptions). The description does not explain any required parameters (month, category_group_id, amount) despite low coverage, leaving their formats and semantics unclear.

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 'Set' and the resource 'budget group amount', distinguishing it from siblings like budget_set_budget_amount which sets individual category amounts. The addition 'may create or update' adds nuance about the operation.

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

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

No guidance on when to use this tool versus alternatives like budget_set_budget_amount or budget_set_budget_group_rollover. No prerequisites or context provided beyond the action itself.

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

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

Annotations already indicate non-read-only and open world behavior. The description adds 'may create or update', but does not elaborate on side effects, permissions, or reversibility. With annotations present, the description could add more value but doesn't.

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 very concise with two short sentences, which is efficient for simplicity. However, it is too sparse to be judged as well-structured; it lacks essential details, so conciseness comes at the cost of completeness.

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

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

With 8 parameters, no output schema, and a complex financial domain (budget rollover), this minimal description is inadequate. It does not explain the concept of rollover, expected inputs, or the effect of changes, making it insufficient for correct tool 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 low (25%). The description does not explain critical parameters like category_group_id, enabled, rollover_type, or starting_balance. It fails to compensate for the under-documented schema, leaving parameter meanings unclear.

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

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

The description states the verb 'set' and resource 'budget group rollover', and adds that it may create or update data, making the purpose clear. However, it does not differentiate from siblings like budget_set_budget_category_rollover or budget_reset_budget_rollover, which have similar names and 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?

The description provides no guidance on when to use this tool versus alternatives. It lacks context on prerequisites, typical scenarios, or exclusions, leaving the agent without decision support.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds 'This may create or update Monarch data,' which is vague and doesn't specify what gets created/updated, permissions needed, or side effects. Minimal added value beyond annotations.

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

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

The description is a single sentence, very concise. It could be front-loaded with more critical information, but it avoids verbosity. Every word earns its place, though more structure would be beneficial.

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

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

Given the tool has 5 parameters, no output schema, and moderate annotations, the description is too brief. It lacks context about return values, behavior on different inputs, and how it fits into the broader budgeting 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?

With 40% schema description coverage and 5 parameters, the description adds no meaning beyond the schema. It does not explain the variability enum values or the purpose of required parameters like category_group_id, leaving the agent without clarity.

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

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

The description states 'Set budget group variability' with a specific verb and resource. It clearly indicates the action, but does not explicitly differentiate from sibling tools like budget_set_budget_category_variability, relying on the name for disambiguation.

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

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

No guidance is provided on when to use this tool versus alternatives such as budget_set_budget_group_amount or budget_set_budget_group_rollover. There is no mention of prerequisites or conditions for use.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds 'may create or update Monarch data,' which is consistent but doesn't disclose any additional behavioral traits such as side effects, authorization requirements, or what 'flex budget' implies. Minimal value beyond annotations.

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

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

The description is very short (two sentences) but lacks essential detail. It is concise but at the cost of completeness, making it barely adequate.

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

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

Given the tool has 7 parameters, no output schema, low schema description coverage, and no sibling differentiation, the description is severely incomplete. It fails to provide sufficient context for correct invocation.

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

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

Schema description coverage is only 29% (2 of 7 parameters have descriptions in the schema). The tool description does not mention any parameters or their meanings, leaving the agent to infer from parameter names alone, which is insufficient for a 7-parameter tool.

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

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

The description states 'Set flex budget amount' which is a verb+resource pair, but it does not explain what a 'flex budget amount' is nor how it differs from other budget-setting tools like budget_set_budget_amount or budget_set_budget_group_amount. It is adequate but vague.

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 sibling budget tools, no prerequisites, and no context on scenarios where setting a flex budget is appropriate. It merely states what it does.

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

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

Annotations already indicate not read-only and not destructive. The description adds 'may create or update Monarch data', which aligns with non-idempotent behavior. However, it doesn't disclose specific side effects or error conditions.

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 concise sentences with no obvious filler. The behavioral note is useful, but the description could be slightly more informative without becoming verbose.

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

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

Given 6 parameters and no output schema, the description fails to explain what flex rollover settings are, the meaning of key parameters, or the expected response. This leaves the agent with significant gaps.

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

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

With only 33% schema coverage, the description provides no additional meaning for parameters like 'enabled', 'start_month', 'starting_balance'. The schema's descriptions for 'fields' and 'output_mode' are already there, so the description adds no value.

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 'Set' and resource 'flex rollover settings', and distinguishes from sibling tool 'budget_get_flex_rollover_settings' via name. However, it does not explain what flex rollover settings are, limiting clarity.

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

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

No guidance on when to use this tool versus alternatives like budget_get_flex_rollover_settings. There is no mention of prerequisites or context for use.

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

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

The description adds no behavioral information beyond what annotations already provide (readOnlyHint, idempotentHint, etc.). It does not explain what the breakdown entails, such as the grouping behavior or the meaning of 'breakdown', thus adding minimal value.

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 vague sentence that essentially repeats the title. While concise, it is under-specified and does not earn its place; useful information is missing.

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 (8 parameters, nested filter input, enums, no output schema), the description is severely inadequate. It does not explain what the breakdown contains, how grouping works, or what the output shape is, leaving agents without crucial 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 only 25% (two parameters have descriptions). The tool description does not elaborate on any of the 8 parameters, including the required direction, start_date, end_date, or optional filters/group_by. With low schema coverage, the description fails to compensate.

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

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

The description 'Get cashflow breakdown' is a tautology that restates the tool name. It fails to clarify what 'breakdown' means (e.g., by category, merchant, period) and does not distinguish it from sibling tools like cashflow_get_cashflow_summary or cashflow_get_cashflow_trends.

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. The sibling tools include summary and trends variants, but the description offers no context on differences or when this breakdown is appropriate.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows it's a safe read operation. The description does not add behavioral context beyond that, but does not contradict annotations.

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

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

The description is one sentence, which is concise, but it is too minimal for the complexity of the tool. It sacrifices informativeness for brevity.

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

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

The tool has 6 parameters, no output schema, and no explanation of return values or behavior. The description is insufficient for an agent to understand the tool's full functionality.

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

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

Schema description coverage is only 33% (2 of 6 parameters have descriptions). The description provides no explanation for parameters, failing to compensate for the low 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 'Get cashflow summary' is a vague verb+resource. It does not specify what the summary includes or how it differs from sibling tools like cashflow_get_cashflow_breakdown or cashflow_get_cashflow_trends.

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 given on when to use this tool versus alternatives. The sibling tools suggest related functionality, but the description offers no 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?

The description adds no behavioral context beyond what annotations already provide (readOnlyHint, idempotentHint). It does not describe output shape, data scope, or any 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?

Extremely concise but at the expense of necessary detail. A single sentence with no structure or partitioning of 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?

Given the tool's complexity (7 parameters, no output schema, multiple siblings), the description is severely incomplete. It does not explain what trends entail, available intervals, filtering options, or output modes.

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 only 29%, but the description provides no parameter details. It fails to compensate for the low coverage, leaving agents without guidance on parameters like filters, interval, or output_mode.

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

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

The description states 'Get cashflow trends,' which provides a verb and resource but is vague. It does not distinguish from sibling tools like cashflow_get_cashflow_breakdown or cashflow_get_cashflow_summary.

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

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

No guidance on when to use this tool versus siblings or alternatives. The description lacks context about use cases 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?

The description adds 'This may create or update Monarch data' which suggests possible side effects beyond creation. Annotations already indicate readOnlyHint=false and destructiveHint=false, so the description provides some extra context about potential updates, but it remains vague and does not specify conditions or extent.

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 very short (two sentences) but the second sentence is vague and could be more precise. It lacks structure and does not efficiently convey essential 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?

The tool has 6 parameters, no output schema, and no explanation of return values or side effects. The description is incomplete for a creation tool; it should describe the expected output (e.g., the created category object) and any consequences like updates to existing categories.

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 only 33%, and the description does not explain any parameters. It adds no meaning beyond what the schema already provides. For a creation tool with 3 required parameters (name, group_id, icon), the description should at least indicate their role.

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

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

The description states 'Create category' which is a specific verb and resource indicating creation. However, adding 'or update' introduces ambiguity about whether it updates existing categories, and it does not differentiate from siblings like categories_create_category_group or categories_update_category.

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. There is no mention of prerequisites, context for creation vs. updating, or comparison with sibling tools such as categories_create_category_group or categories_update_category.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds the note 'This may create or update Monarch data', which hints at potential upsert behavior but does not clarify idempotency (idempotentHint=false). Overall, minimal additional value beyond annotations.

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

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

The description is very short (two sentences) and front-loaded with the core purpose. However, the second sentence is vague and does not add substantial value, making it slightly less efficient than ideal.

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 moderate complexity (5 parameters, no output schema), the description is insufficient. It does not explain what the response looks like, how to handle the 'type' enum, or the effect of optional parameters like 'fields' or 'output_mode'.

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

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

Schema coverage is only 40% (2 of 5 parameters documented), yet the description adds no parameter information. It fails to explain the meaning of 'name', 'type', or other fields, leaving the agent without necessary guidance for correct invocation.

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 'Create' and resource 'category group', making the tool's purpose unmistakable. It distinguishes itself from sibling tools like categories_delete_category_group and categories_update_category_group.

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

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

The description provides no guidance on when to use this tool versus alternatives such as categories_create_category or other category tools. There is no mention of context, 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?

The annotations already declare destructiveHint=true, so the description merely restates that fact without adding new behavioral insights. No mention of side effects, required permissions, or reversibility.

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 very short, but the second sentence is vague and adds noise without value. It could be improved by being more precise rather than adding redundant qualifiers.

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 destructive tool with 5 parameters and no output schema, the description is woefully inadequate. It fails to explain what happens to categories within the group, the effect of move_to_group_id, or the behavior of other parameters.

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

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

Schema description coverage is only 40%, and the description adds no explanation for any parameter. Critical parameters like group_id and move_to_group_id are left completely undocumented.

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

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

The description clearly states 'Delete category group' which is a specific verb+resource. It distinguishes from siblings like 'categories_remove_category' as it targets a group, not an individual category. However, the additional vague phrase 'This may delete, clear, reset, or otherwise remove data' adds confusion without clarifying what actually happens.

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

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

No guidance on when to use this tool vs alternatives, no prerequisites mentioned. The description is purely operational and does not provide context for appropriate 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which sufficiently indicate this is a safe, read-only operation. The description does not add any additional behavioral context beyond what the annotations provide, so no extra value is added.

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 (one sentence), but it is under-specified. It does not earn its place by providing valuable context; it merely restates the obvious from the tool name. A more informative description would be appropriate.

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

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

Given the tool has 4 parameters, no output schema, and the description is minimal, the tool lacks sufficient context for an agent to use it correctly. Important details like the return value shape, error conditions, or usage notes are missing.

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%, with some parameters (fields, output_mode) having descriptions in the schema. However, the tool description 'Get category.' provides no information about any parameters, such as the required category_id. The description fails to add meaning beyond the schema.

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

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

The description 'Get category.' clearly indicates the verb and resource (get a single category). It distinguishes from sibling tools like categories_list_categories or categories_get_category_catalog because those have distinct names and purposes. However, it doesn't explicitly state that it retrieves a category by ID, which is implied by the required category_id parameter.

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 categories_list_categories (which retrieves all categories) or categories_get_category_group. The description lacks context for selection.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, which cover safety but not behavior. The description adds no additional behavioral context (e.g., return format, filtering).

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?

Extremely concise (4 words) but lacks essential details, making it under-specified rather than efficiently succinct. Not front-loaded with critical 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?

Given 4 parameters, no output schema, and annotations present, the description is too sparse to be complete. It omits return values, parameter interactions, and usage 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 50% (2 of 4 parameters described). The description does not mention any parameters or add meaning beyond the schema, failing to compensate for undocumented parameters like session_path and include_disabled.

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

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

The description states it retrieves the category catalog, but it lacks specificity compared to sibling tools like categories_list_categories. 'Catalog' is ambiguous and does not differentiate scope or structure.

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

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

No guidance on when to use this tool versus alternatives such as categories_get_category or categories_list_categories. Missing context for appropriate 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds no additional behavioral context beyond the literal action. It does not contradict annotations, but also does not elaborate on return structure 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?

The description is extremely concise (three words) and to the point. While it lacks richness, it is appropriately brief for a simple retrieval tool. No unnecessary content.

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

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

Given the tool's simplicity and the presence of annotations covering safety, the description is minimally adequate. However, it does not explain the purpose of parameters like 'output_mode' or that the tool requires a 'group_id'. The lack of output schema is not mitigated by the description.

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%, with descriptions for 'fields' and 'output_mode' but none for 'group_id' or 'session_path'. The tool's description does not clarify any parameters or add meaning beyond the schema's existing 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 'Get category group', which is a specific verb and resource. It distinguishes from sibling tools like 'categories_list_category_groups' (list) and 'categories_get_category' (different resource). However, it does not explicitly mention that it retrieves a single group by ID, though that is implied by the required 'group_id' parameter.

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 'categories_list_category_groups' or 'categories_get_category'. There is no mention of context 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?

Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds no extra behavioral traits beyond what annotations imply. It does not mention any constraints like pagination or data limits, but annotations cover the safety profile.

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 (two words). While it is front-loaded, it is perhaps too minimal for a tool with 5 parameters and no output schema, but it does not waste words.

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

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

Given 5 parameters (including nested filters) and no output schema, 'List categories' is insufficient. It lacks information about filtering options, output modes, pagination, or any behavioral details beyond the bare minimum.

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 40% (only fields and output_mode have descriptions). The description does not explain any parameters, including filters, session_path, and include_disabled. With low coverage, the description should compensate but fails to do so.

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 'List categories' clearly states the verb and resource. It distinguishes from siblings like categories_get_category (single) and categories_list_category_groups (groups), as the tool specifically lists categories.

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

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

No guidance on when to use this tool vs alternatives such as categories_get_category for a specific category or categories_list_category_groups for groups. The description lacks context about filtering or scope.

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

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

The description adds no behavioral context beyond what annotations already provide (read-only, idempotent, non-destructive). It does not disclose ordering, pagination, filtering, or return structure. With annotations covering safety, the description still fails to add any value.

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, but it does not earn its place as it adds no information beyond the title. It is underspecified rather than efficiently concise.

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

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

For a list operation with no output schema, the description should explain the return shape or behavior. It does not. Given the tool's simplicity and sibling context, the description is incomplete.

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 description does not reference any of the three parameters (fields, output_mode, session_path). Schema coverage is 67%, but the description adds no additional meaning or hints about how to use the parameters effectively.

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 'List category groups.' is a tautology that merely restates the tool title without adding any specificity about what category groups are or how they relate to categories. It does not distinguish from siblings like 'categories_list_categories' or 'categories_get_category_group' beyond the resource 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 usage guidance is provided. The description does not indicate when to use this tool versus alternatives (e.g., when to list categories vs. category groups, or when to get a single group). There is no mention of prerequisites or context.

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

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

The description adds 'may create or update Monarch data,' which expands on the annotations (readOnlyHint=false, destructiveHint=false). However, it lacks details like side effects of reactivating an already active category or required permissions. Annotations already cover safety, so the description provides moderate added value.

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 (two sentences) with no redundancy. Every word is necessary, making it easy to parse. It is well-structured and front-loaded.

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

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

Given the lack of output schema and 4 parameters, the description is too sparse. It does not explain what 'reactivate' means operationally, what the response contains, or any important constraints. For a tool with many siblings, more context would improve usability.

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

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

With 50% schema description coverage, the description does not add any parameter-specific context. Two parameters (category_id, session_path) lack schema descriptions and are not explained in the description. The existing schema descriptions for 'fields' and 'output_mode' are adequate, but the overall contribution is minimal.

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 ('Reactivate category') and resource, distinguishing it from siblings like 'categories_remove_category' or 'categories_create_category'. However, it does not elaborate on what reactivation entails (e.g., making an inactive category active), leaving some ambiguity.

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 does not mention prerequisites, typical scenarios, or when not to use it, leaving the agent without decision support.

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

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

Annotations already indicate destructiveHint=true and readOnlyHint=false. The description adds 'This may delete, clear, reset, or otherwise remove data,' which is vague and does not clarify the specific behavior (e.g., whether transactions are moved or deleted). It fails to disclose side effects beyond the obvious destructive nature.

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 very short (two sentences), but the second sentence is vague and wastes words. It could be more concise by removing the redundant phrasing and instead focusing on key behavior or parameters. It is not efficiently 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 has 5 parameters, one required, and no output schema, the description is incomplete. It does not explain the core action (permanent removal? moving transactions?), and it ignores important context like the role of move_to_category_id. The description fails to provide a complete understanding for an 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 coverage is 40%, with only fields and output_mode having descriptions. The description does not mention any parameters, so it provides no additional meaning for undocumented parameters like category_id and move_to_category_id. It does not compensate 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 states 'Remove category,' which clearly identifies the action and resource. However, the second sentence 'This may delete, clear, reset, or otherwise remove data' is confusing and ambiguous, detracting from clarity. The tool is distinguishable from siblings like categories_delete_category_group, but the description does not explicitly differentiate it.

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 does not mention prerequisites, when not to use it, or what to use instead (e.g., deactivating via categories_reactivate_category). The parameter move_to_category_id suggests an important workflow, but it is not explained.

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

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

Annotations already indicate this is a modifying operation (readOnlyHint=false) and not destructive. The description adds the vague warning that it 'may create or update Monarch data,' which provides some additional context beyond annotations, but it is not specific about what data might be created or the conditions under which creation occurs.

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 very short (two sentences), which is concise but at the expense of necessary detail. Given the tool has 6 parameters and no output schema, the description is too brief to be adequately informative. Front-loading is acceptable but the content is insufficient.

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

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

The tool has 6 parameters, no output schema, and low schema coverage. The description fails to explain the return value, the effect of parameters like 'output_mode', or how the reordering operation works. It is incomplete relative to the tool's complexity.

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

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

With only 33% schema description coverage, the description should compensate by explaining key parameters like 'order', 'category_id', and 'group_id'. However, the description contains no parameter explanations at all, leaving the agent to infer meaning solely from parameter names, which is insufficient.

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 'Reorder' and the resource 'category', but lacks specificity about the scope of reordering (e.g., within a group) and does not differentiate from the sibling tool 'categories_reorder_category_group'. The addition of 'This may create or update Monarch data' slightly muddles the purpose but does not make it misleading.

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 'categories_reorder_category_group' or other category modification tools. There is no mention of prerequisites, context, or exclusions, leaving the agent without decision support.

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

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

Annotations indicate readOnlyHint=false and destructiveHint=false. The description adds 'This may create or update Monarch data,' which is consistent but adds little beyond annotations. No disclosure of side effects or permission needs.

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

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

The description is concise at two sentences, front-loading the core action. However, it sacrifices helpful detail for brevity.

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

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

The tool has 5 parameters, no output schema, and requires reordering logic. The description is too minimal to provide complete guidance; it omits return behavior, ordering semantics, and impact on data.

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

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

With only 40% schema description coverage, the tool description adds no parameter information. It does not explain how 'order' works or provide context beyond what the schema already offers.

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 ('Reorder category group') and distinguishes it from siblings like 'categories_reorder_category' by specifying 'category group'. However, it could be more specific about what reordering entails.

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

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

No guidance is provided on when to use this tool versus alternatives (e.g., 'categories_reorder_category' for groups). No context on prerequisites or 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?

Annotations already declare readOnlyHint false and destructiveHint false. The description adds 'This may create or update Monarch data', hinting at an upsert behavior which is not captured by annotations. However, it lacks specifics on side effects, authorization, or reversibility.

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 very short at two sentences. It front-loads the purpose, but the second sentence ('This may create or update Monarch data.') is vague and could be removed or clarified. Overall efficient but could be more precise.

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 7 parameters and no output schema, the description is inadequately complete. It does not specify what fields can be updated, the required parameter (category_id), or the outcome. The low schema coverage intensifies this gap.

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 only 29% schema description coverage, the description compensates poorly by not explaining any parameters. It omits details on what aspects of a category can be updated (e.g., name, icon, group_id). The schema's field descriptions are minimal, and the description adds zero value for 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 'Update category', identifying the specific verb and resource. The name and title also make the purpose clear. However, it does not distinguish from sibling tools like categories_update_category_group, and the ambiguous 'may create' slightly dilutes the clarity.

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

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

No guidance on when to use this tool versus alternatives like categories_create_category or categories_remove_category. No context provided about prerequisites or typical use cases.

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

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

Annotations already indicate a write operation (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds 'may create or update,' which is vague and could imply creation despite the tool name. No additional behavior (e.g., auth needs, reversibility) is disclosed.

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 very short (one sentence), which is concise and front-loaded. However, it sacrifices useful detail. It is well-structured for brevity but could be improved by adding more structured information without increasing length significantly.

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 six parameters, a required group_id, no output schema, and the complexity of category group management, the description is highly incomplete. It does not explain what a category group is, what the parameters do, what the return value looks like, or how this tool fits into the broader workflow. The agent would be severely underinformed.

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 33%, meaning only 'fields' and 'output_mode' have descriptions. The tool description does not explain any parameter beyond what the schema provides. For parameters like 'group_id', 'name', and 'type', the agent must infer meaning from context; the description adds no value.

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

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

The description states 'Update category group,' which is a clear verb+resource. However, it adds 'This may create or update Monarch data,' creating ambiguity since there is a separate 'categories_create_category_group' sibling tool. The agent might be confused whether this tool can create groups or should only update existing ones.

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 its siblings, such as 'categories_create_category_group' or 'categories_delete_category_group'. The agent receives no context about prerequisites, typical use cases, or when not to use this tool.

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

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

Annotations show non-read-only and non-destructive, but the description only adds 'may create or update Monarch data', a generic statement that does not explain the specific state change (e.g., setting an 'archived' flag). No mention of reversibility 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?

The description is very short (two sentences), but the second sentence is vague and unhelpful. It could be restructured to prioritize the effect of archiving over the generic data creation/update statement.

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 four parameters, no output schema, and similar sibling tools, the description is incomplete. It lacks explanation of return values, the effect on the goal's state, and parameter details beyond what the schema provides.

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 description does not reference any parameters. Although schema description coverage is 50% (fields and output_mode have descriptions), the required goal_id lacks explanation. The description should clarify that goal_id identifies the goal to archive.

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

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

The description states 'Archive goal', a specific verb+resource, but does not clarify what archiving means (e.g., marking as inactive) versus deleting or restoring. The vague second sentence about creating/updating data adds confusion and fails to distinguish this tool from siblings like goals_delete_goal.

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 goals_delete_goal or goals_restore_goal. Prerequisites (e.g., goal must exist, cannot already be archived) are omitted.

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

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

Annotations already indicate readOnlyHint=false and destructiveHint=false. The description adds 'This may create or update Monarch data,' which is largely redundant with the annotations. It omits behavioral details like side effects, required permissions, or return value 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 concise at two sentences, but the second sentence is vague and not actionable. It could be restructured to front-load the primary action and provide more useful constraints.

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

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

For a tool with 9 parameters, 3 required, and no output schema, the description is severely incomplete. It fails to explain what a contribution is, how the goal and account parameters relate, or what the tool returns.

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 only 22% schema description coverage, the description should compensate but adds no parameter details. The schema provides some descriptions (e.g., for 'fields' and 'output_mode'), but the description does not enhance understanding or usage of the 9 parameters.

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

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

The description 'Contribute to goal' indicates a verb-resource action, but it is vague and does not specify what 'contribute' entails (e.g., adding funds, recording progress). It fails to differentiate from sibling tools like goals_create_goal or goals_update_goal.

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

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

No guidance is provided on when to use this tool versus alternatives, such as goals_create_goal or goals_withdraw_from_goal. There is no mention of prerequisites or contextual constraints.

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?

Annotation already indicates readOnlyHint=false. Description adds minimal context ('may create or update') but is vague and doesn't disclose side effects beyond annotations.

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

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

Two sentences, efficient but second sentence is vague. Could be more precise without extra words.

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

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

Given 12 parameters and no output schema, the description is too sparse. Lacks explanation of return values, creation behavior, or parameter relationships.

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 only 17%, leaving most parameters undocumented. Description provides no additional parameter meaning.

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

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

Description states 'Create goal' but adds vague 'may create or update Monarch data' which confuses the purpose. Does not distinguish from goals_update_goal.

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

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

No guidance on when to use this tool vs alternatives. Does not specify 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?

The description states it is destructive, matching annotations (destructiveHint:true). However, it is vague about what exactly happens (e.g., cascading effects on goal events). Minimal additional value beyond annotations.

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

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

The description is concise at one sentence. While not structured with bullet points or sections, it is front-loaded with the action. Could include more key info 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 destructive tool with no output schema, the description lacks essential context: permanence, what happens to associated data (e.g., goal events), and how to verify deletion. Incomplete for safe agent 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?

With 50% schema description coverage, the tool description adds no parameter explanations. The schema describes fields and output_mode, but not goal_id or session_path. Description fails to compensate for the gap.

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 'Delete goal,' indicating the action and resource. It distinguishes from siblings like goals_archive_goal by focusing on deletion, but could be more specific about what deletion entails beyond 'may delete, clear, reset, or otherwise remove 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 guidance on when to use this tool vs alternatives like archiving or the related goals_delete_goal_event. Given destructiveHint:true, it would be helpful to note that deletion is irreversible and suggest archiving as a safer alternative.

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

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

Annotations already provide destructiveHint=true and readOnlyHint=false, clearly indicating a destructive operation. The description adds minimal value by stating it may 'delete, clear, reset, or otherwise remove data,' which is partially redundant and vague.

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, front-loaded with the core action. The second sentence is vague but short. Overall efficient with no 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?

For a destructive operation with 4 parameters and no output schema, the description lacks detail on return behavior, side effects, or specifics of what 'delete, clear, reset' means in practice. The tool's purpose is clear but not fully contextualized.

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 50% schema description coverage, the description does not add any parameter explanations. Required 'event_id' and optional 'session_path' lack context, and the description does not compensate for these 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 states 'Delete goal event,' clearly identifying the action and resource. However, the vague addition 'This may delete, clear, reset, or otherwise remove data' does not differentiate it from similar tools like goals_delete_goal or goals_update_goal_event.

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

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

No guidance on when to use this tool versus alternatives like goals_delete_goal or goals_update_goal_event. Context signals indicate sibling tools exist but description lacks any 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds no additional behavioral context (e.g., what fields are returned, authentication needs, or side effects), so it provides minimal value beyond the annotations.

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

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

While very short (two words), the description is under-specified and omits essential information. True conciseness would include critical details about usage and 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?