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

No annotations are provided, so the description carries the full burden. It only lists operations and says 'basic arithmetic', which repeats the schema's enum. It does not disclose edge-case behaviors like division by zero, square root of negative numbers, or return format, which are important for a calculator tool.

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

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

The description is a single, front-loaded sentence with no filler. It concisely conveys the tool's scope and supported operations.

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 potential failure modes (e.g., divide by zero, sqrt of negative) and no output schema, leaving the agent unaware of return values or error handling. The schema captures parameter types but the description adds no behavioral context beyond a listing of operations, making it incomplete for safe 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 100%, providing descriptions for all parameters. However, the description says 'on two numbers' which is misleading for sqrt, which uses only one operand. This internal inconsistency detracts from the schema's 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 clearly states the tool performs basic arithmetic operations, listing specific supported operations (add, subtract, multiply, divide, power, sqrt). This distinguishes it from sibling tools, which are unrelated (e.g., echo, read_file, create_project).

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

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

The description implies this is for basic arithmetic, which is clear context. Since no sibling tool performs similar arithmetic, explicit exclusions are unnecessary. However, it lacks guidance on when to prefer this over, say, a more specialized calculator tool (none exist here).

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

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

No annotations are provided, so the description carries the full burden. It discloses mutation ('creates a new') but does not mention return values, validation behavior, potential errors, or side effects. For a create operation, it could state whether the created document is returned or whether duplicates are allowed.

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 front-loaded with the action, wasting no words. It is appropriately sized for a simple create tool.

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

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

The tool is a simple create operation with rich schema coverage, but the description lacks return-value information and usage context. Given no annotations and no output schema, additional details about expected response or edge cases would improve completeness.

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

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

All four parameters are fully described in the schema (100% coverage), so the description need not explain them. The description adds no additional parameter meaning, so the baseline of 3 applies.

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

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

The description clearly states a specific verb ('creates') and resource ('knowledge base article') in a specific store, making the purpose evident. It implicitly distinguishes from sibling create_project, but does not explicitly contrast with update_document or other create tools.

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

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

The description provides no guidance on when to use this tool versus alternatives like create_project or update_document. 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only states the action and target, without mentioning side effects, return behavior, permissions, or any other behavioral traits. This is a significant gap for a mutation tool.

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

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

The description is a single, front-loaded sentence with no redundant words, effectively communicating the core purpose. It is concise and well-structured, earning its place without unnecessary elaboration.

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

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

Despite having a clear purpose and complete parameter schema, the description lacks context about return values, successful behavior, or any operational details. Since there is no output schema, the description should at least indicate what the tool returns, 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?

The input schema has 100% description coverage for all four parameters, providing meaningful semantics without relying on the tool description. The description adds no extra parameter details, but the schema already handles this adequately.

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 explicitly identifies the action ('creates'), the resource ('a new project'), and the context ('mock project management system'), making it unambiguous. It clearly distinguishes from sibling tools like create_document or update_project by specifying 'project' as the target.

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

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

The description implies usage for creating projects, but it does not explicitly state when to prefer this over similar tools (e.g., create_document) or provide exclusions or prerequisites. It lacks guidance on alternative scenarios.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently states that the tool returns server time (not local/client time), accepts an IANA timezone, and defaults to UTC. It also implies a read-only operation with no side effects. While it doesn't detail error handling or output format, the core behavior is clearly 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, well-structured sentence that front-loads the action ('Returns the current server time') and includes necessary context (IANA timezone, default UTC). Every word is informative, and there is no redundant or filler content.

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

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

This is a low-complexity tool with one optional parameter and an output schema present. The description adequately covers the tool's purpose and input behavior. Since an output schema exists, the description does not need to explain return values. The description is complete enough for an agent to correctly select and invoke the tool.

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

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

The input schema provides 100% coverage of the 'timezone' parameter, including its IANA format and default value. The description adds example timezone names, but this information is already in the schema description. Therefore, the description adds minimal semantic value beyond the structured schema, warranting the baseline score of 3.

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

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

The description clearly states what the tool does: 'Returns the current server time in the requested IANA timezone.' It uses a specific verb and resource, and provides concrete examples of timezone values. This distinguishes it from sibling tools like echo, calculate, or random_number, which have entirely different 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 implies usage: use this when you need the current server time, optionally in a specific timezone. However, it does not explicitly mention alternatives or when not to use it compared to other tools. There is no direct guidance on tool selection relative to siblings, so it falls to 'implied usage' rather than clear contextual differentiation.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the exact behavior (echoing back text) and frames it as a connectivity check, implying no side effects or state changes. While it doesn't explicitly say 'read-only' or 'no side effects,' the nature of an echo tool makes this strongly implicit.

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

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

The description is two short sentences, front-loaded with the core action and followed by a practical use case. Every word earns its place with zero redundancy or filler.

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

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

This is a trivially simple tool with one parameter and no output schema. The description fully covers its purpose, behavior, and recommended use context. Nothing important is missing for an agent to correctly select and invoke this tool.

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

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

The input schema describes the single parameter 'text' as 'The text to echo back,' achieving 100% schema coverage. The tool description adds no additional meaning about parameter constraints, format, or limits. With full schema coverage, the baseline score of 3 is appropriate.

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

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

The description clearly states 'Echoes back the text you send,' which is a specific verb+resource action. It is unambiguous and distinct from all sibling tools such as calculate, read_file, or create_document. No other tool suggests echoing input, so it stands alone.

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

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

The description explicitly provides a use case: 'Useful as a connectivity check to verify the server is reachable.' This gives clear context for when to invoke the tool. It does not mention alternatives or when-not-to-use, but for such a simple utility this is sufficient.

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

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

With no annotations provided, the description must carry the full burden of behavioral transparency. It states what the tool returns but does not disclose whether the operation is read-only, whether it requires specific permissions, or any potential side effects. The name suggests a read operation, but the description does not explicitly confirm safety or limitations.

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

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

The description is a single, well-structured sentence that front-loads the main purpose ('Returns server health metrics') and then lists specific metrics. Every word contributes meaning, with no repetition or filler.

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

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

Given the simplicity of the tool (one optional parameter) and the presence of an output schema, the description is reasonably complete. It explains what the tool returns, and the schema covers the parameter. However, it lacks usage guidance and explicit safety information, which would improve completeness.

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

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

The input schema fully documents the only parameter (includeMemory) with a description and default value, so baseline is 3. The tool description adds no additional information about the parameter or its effect, but since schema coverage is 100%, no compensation is needed.

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

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

The description clearly states the tool returns server health metrics including uptime, request count, memory usage, and OAuth provider configuration summary. It uses a specific verb ('Returns') and names the resource ('server health metrics'), but does not explicitly distinguish it from sibling tools like query_analytics or list_server_capabilities.

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

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

The description implies usage when server health metrics are needed, but provides no explicit guidance on when to prefer this tool over alternatives or when not to use it. There is no mention of exclusions or prerequisites, so the guidance is only implicit through the stated purpose.

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

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

With no annotations provided, the description carries the full burden. It discloses that the tool operates on a 'mock file system,' which is a key behavioral context. It also implies a read-only operation via 'lists,' though it does not detail error handling or hidden-file behavior. Still, the disclosure is adequate for this simple tool.

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

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

The description is two sentences, front-loaded with the purpose and immediately followed by a concrete usage example. Every word earns its place with no redundancy.

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

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

For a one-parameter list tool with no output schema, this description covers the essential context: what it lists, the mock nature, and how to specify paths. No further information is needed for an agent to select and invoke it correctly.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reiterates the schema's 'Use '/' for root' and adds a multi-level path example, but this is marginal extra meaning beyond what the schema already provides.

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

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

The description uses a specific verb and resource: 'Lists files and directories in a mock file system.' This clearly distinguishes it from sibling tools like read_file, upload_file, and list_projects, which target different resources or 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?

The description provides explicit usage guidance with examples: 'Use '/' to see the root, or a directory path like '/project/src' for subdirectories.' It gives concrete context on how to invoke the tool, though it does not explicitly discuss alternatives 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?

With no annotations, the description must communicate behavioral traits, but it only states the tool lists mock projects, implying a read operation without detailing permissions, side effects, or return format. The mention of an 'owner' filter that isn't in the schema is misleading, further reducing transparency.

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

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

The description is a single, concise sentence that front-loads the primary action. The unnecessary 'owner' mention is an inaccuracy, but structurally it is clean and easy to parse.

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

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

For a simple list tool with two optional filters, the description covers the basic purpose and filter capability. However, it lacks details about response format, pagination, or any usage context, and the inaccurate owner filter creates a gap. Overall, it is minimally sufficient but not thorough.

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 already provides clear descriptions for the two parameters (status and tag), so the baseline is 3. However, the description introduces an 'owner' filter that is not a real parameter, which adds confusing and inaccurate semantics beyond the schema.

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

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

The description clearly states the tool lists projects, with a specific resource ('projects') and action ('lists'). It also mentions optional filters, distinguishing it as a listing operation. However, it inaccurately claims an 'owner' filter that does not exist in the schema, which slightly detracts from 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 is provided on when to use this tool versus alternatives like search_documents or query_analytics. The phrase 'mock projects' implies a testing context, but there are no explicit exclusions or alternative suggestions, leaving the decision to the agent.

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

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

With no annotations, the description must carry behavioral disclosure. It adds a useful detail: results are 'grouped by scope requirement.' However, the meaning of 'scope requirement' is not explained, leaving some ambiguity about the output structure. The tool is inherently read-only, but this is not explicitly stated, though it is fairly obvious.

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

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

The description is a single, clear sentence that delivers all essential information without redundancy. It is front-loaded with the verb and resource, making it easy to scan. No word is wasted.

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 zero-parameter, no-output-schema tool, this description is mostly complete. It tells the agent what the tool lists and hints at the grouping structure. However, it could briefly mention that this is the canonical way to discover capabilities, and it might clarify what 'scope requirement' refers to, but overall it is sufficient for the tool's simplicity.

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

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

The tool has zero parameters, so the schema is fully covered (100%). The description correctly avoids inventing parameter details. With no parameters, a baseline of 4 is appropriate because there is nothing to explain; the description's mention of grouping refers to output structure, not input semantics.

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

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

The description clearly states the tool's purpose: 'Lists all available tools, resources, and prompts that this server exposes.' It uses a specific verb ('lists') and resource ('available tools, resources, and prompts'). It also distinguishes itself from all sibling tools, which are domain-specific, by being a server introspection tool.

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

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

The description implies usage as a discovery mechanism but does not explicitly state when to use it versus alternatives. Since no sibling tool performs a similar discovery function, the lack of explicit 'when not to use' is acceptable, but the guidance is still only implied rather than clearly articulated.

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

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

With no annotations provided, the description carries full responsibility for behavior disclosure. It does add the 30-day window and the type of data returned, which gives some transparency about the query scope. However, it does not disclose the response format, pagination, or behavior when date parameters are omitted or exceed the 30-day window, leaving ambiguity.

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

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

The description is a single, well-front-loaded sentence that states the action, resource, and key details without any superfluous information. Every word earns its place, making it highly concise and easy to parse.

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

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

The tool is relatively simple with only three parameters and no output schema, so the description covers the core purpose. However, the interplay between the '30-day window' and arbitrary startDate/endDate parameters is unclear—does it represent a default, a maximum, or a fixed range? Also, without an output schema, the description would benefit from explaining what the query returns for each metric value, 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?

The schema already provides 100% coverage for all three parameters, so the baseline is 3. The description adds extra meaning by indicating the 30-day window, which likely relates to how startDate and endDate are interpreted, and by naming the metrics that correspond to the 'metric' enum options (e.g., daily, features). This goes beyond simply restating the schema.

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

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

The description clearly states the tool queries mock analytics data and specifies the exact metrics (daily active users, revenue, churn rate, feature usage) and a 30-day window. This uses a specific verb ('Query') and resource ('analytics data'), and it fully distinguishes itself from the sibling tools, none of which deal with analytics.

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

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

Usage context is implied: use this tool to query analytics data. However, there is no explicit guidance on when to use it versus alternatives, nor any exclusions or prerequisites. The mention of 'mock' data hints that it is not for real data, but this is not stated as a direct usage guideline.

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

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

With no annotations, the description carries the burden. It discloses the core behavior: random integer, inclusive bounds. However, it doesn't mention edge-case handling (e.g., min > max) or the distribution, leaving some ambiguity for error-prone inputs.

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

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

A single sentence that is direct and information-dense, with no unnecessary words or repetition.

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

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

For a simple tool with no output schema and no complex parameters, the description fully captures the behavior: it returns a random integer within the specified inclusive range. It is sufficient for an agent to use it correctly.

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

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

Schema coverage is 100%, with both 'min' and 'max' described as inclusive bounds. The description reinforces this with the [min, max] notation but adds little beyond what the schema already provides.

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

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

The description clearly states the tool's action ('Generates a random integer') and its key scope (inclusive range [min, max]). This distinguishes it from siblings like 'calculate' and 'current_time' which serve different functions.

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

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

The description implies its use case: when a random integer within a specified inclusive range is needed. It doesn't explicitly discuss exclusions or alternatives, but for a simple generator, the context is clear enough.

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

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

No annotations are provided, so the description carries the full burden. It discloses that this reads a 'mock' file and specifies the path format, implying a read-only operation. However, it does not mention error handling, return format, or explicitly confirm non-destructiveness beyond the verb 'reads'.

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

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

The description is two sentences, directly stating the action and providing an example. It is front-loaded, efficient, and contains no unnecessary words or repetition.

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

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

For a simple one-parameter read tool with no output schema, the description covers the essential action and parameter guidance. It does not explicitly state the return value format or error behavior, but the low complexity and clear verb 'reads' make this adequate for selection and invocation.

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

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

Schema coverage is 100%, with the path parameter already described in the schema. The description adds a concrete example path and emphasizes 'full path', providing slight value beyond the schema, but does not add significant semantic detail beyond what is already documented.

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 reads the contents of a mock file from the file system, using a specific verb ('Reads') and resource. It distinguishes from sibling tools like list_files or upload_file by focusing on reading existing file contents, and the example path clarifies the expected input format.

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

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

The description implies the use case (read a file's contents) but does not explicitly compare to alternatives or state when not to use it. It provides no exclusions or references to sibling tools, so usage guidance is only implicit.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions that the reload is 'hot' and reads 'from disk,' but it does not disclose side effects, prerequisites (e.g., admin permissions), error behavior, or whether the reload affects other components. This leaves significant behavioral ambiguity.

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

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

The description is two short sentences that get straight to the point: 'Hot-reloads the OAuth provider configuration from disk. Useful after updating scopes or provider settings.' No wasted words, and the most essential 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's simplicity (zero parameters, no output schema), the description covers the core purpose and a common use case. It is missing details like error handling or preconditions (e.g., config file must exist), but for a straightforward reload action, it is reasonably complete.

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

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

The tool has zero parameters, so the input schema is empty and there is nothing to document. The baseline for no params is 4, and the description correctly does not invent parameter details. It adds no parameter-specific meaning, but none is needed.

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

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

The description clearly states the tool's function with a specific verb and resource: 'Hot-reloads the OAuth provider configuration from disk.' This unambiguously identifies what the tool does and distinguishes it from any sibling tools, none of which handle configuration.

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 a clear usage context: 'Useful after updating scopes or provider settings.' This tells the agent when the tool is appropriate. However, it does not explicitly mention when not to use it or alternative tools, so it loses a point for lacking exclusions 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?

With no annotations, the description carries the burden. It discloses the tool performs full-text search over a mock knowledge base and covers specific topics, adding context beyond the schema. However, it does not mention result sorting, pagination, or read-only nature, leaving some behavioral gaps.

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

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

The description is a single sentence with no wasted words, immediately stating the verb and resource. It is well-structured and easy to parse.

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

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

Given the output schema exists and the input schema fully documents parameters, the description provides sufficient context about the mock knowledge base and topics. It lacks an explicit note about read-only behavior or result count limits, but these are inferable from the schema. For a simple search tool, this is adequate.

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

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

The input schema has 100% description coverage for all parameters, so the baseline is 3. The description adds context about the search scope but does not elaborate on individual parameters beyond what the schema already provides.

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

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

The description clearly states a specific action (full-text search) on a defined resource (mock knowledge base of 15+ articles), with scope (categories). This distinguishes it from sibling tools like read_file or list_files, which do not offer search functionality.

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 context implies the tool is for searching the knowledge base, but there is no explicit when-to-use guidance or exclusions. Since no sibling tools perform search, usage is inferable but not explicitly stated.

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

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

Annotations are absent, so the description carries the full burden. It explicitly states it computes statistics, implying a pure, non-mutating operation. However, it does not disclose edge-case behavior (e.g., NaN, Infinity) or side effects, but for a simple computation tool, this is 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?

The description is a single, well-organized sentence that front-loads the purpose and lists all statistics, with no wasted words or redundancy.

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

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

The tool is simple (one parameter) and has an output schema, so return values don't need to be in the description. The description covers purpose and parameters sufficiently, but lacks explicit usage context; still, it is complete enough for a tool of this 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?

The input schema already has 100% coverage, describing 'numbers' as 'A non-empty list of numbers'. The description repeats 'list of numbers' without adding any additional parameter semantics, so it meets the baseline of 3 but adds no extra 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 uses a specific verb 'computes' and clearly specifies the resource 'a list of numbers' along with the exact statistics (count, sum, min, max, mean, median, standard deviation). This fully distinguishes it from sibling tools like 'calculate' or 'random_number'.

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

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

The description implies usage for summarizing numeric lists but does not explicitly state when to use it over alternatives like 'calculate' or exclude non-list cases. No direct comparison or when-not-to-use guidance is provided.

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

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

With no annotations, the description carries the full burden of behavioral disclosure. It does not explain whether this is a partial or full update, what happens if the document does not exist, or whether changes are reversible. The single sentence provides no behavioral context beyond the schema.

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

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

The description is a single, front-loaded sentence that immediately states the core purpose. It wastes no words and is appropriately sized for the simplicity of the tool, though it lacks 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?

Despite low complexity and full schema coverage, the description is too sparse for a mutation tool. It does not cover key behavioral aspects like partial update semantics, error handling, or return value, especially since annotations are absent and there is no output schema.

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

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

Schema description coverage is 100%, so the schema already documents all four parameters. The description adds no extra semantics about how parameters interact (e.g., whether tags replace or merge), so it stays at the baseline of 3.

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

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

The description clearly states the action ('Updates') and the resource ('existing knowledge base article'). The word 'existing' distinguishes this from create operations, and the resource type is specific enough to differentiate from other update tools like update_project.

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

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

The description implies usage for updating existing articles, but does not explicitly state when to use this tool versus alternatives like create_document. No exclusions or prerequisites are mentioned, so guidance is only implied by the word 'existing'.

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

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

No annotations are present, so the description must fully convey behavioral traits. It indicates mutation ('Updates') but does not disclose whether fields are partially updated or replaced, whether the operation requires special permissions, or what the response looks like. This leaves significant behavioral ambiguity for a mutation tool.

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

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

The description is a single concise sentence that front-loads the core purpose. However, the word 'details' is vague and could be interpreted as a catch-all, slightly reducing precision while maintaining 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 four parameters, no output schema, and no annotations, so the description must carry more weight. It fails to mention required parameters, update semantics, return behavior, or any side effects. This is insufficient for an agent to confidently invoke the tool.

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

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

The input schema provides full documentation for all four parameters (id, status, deadline, progressPercent), so the description adds little beyond that. It lists 'status' and 'progress' which map to schema properties, but does not explain id or deadline semantics beyond what the schema already provides.

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

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

The description clearly states the tool updates a project's status, progress, or details. It uses a specific verb ('Updates') and resource ('project'), and distinguishes itself from sibling tools like update_document by focusing on projects rather than documents.

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 exclusions or prerequisite conditions, leaving the agent to infer usage solely from the tool's name and description.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly states 'overwrites,' which is a key destructive behavior, and 'mock file system' sets expectations about the environment. It doesn't mention other side effects (e.g., permission checks, parent directory creation), but for a simple tool, the overwrite disclosure is valuable.

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

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

The description is two concise sentences. The first states the purpose and behavior, the second tells the user what to provide. No redundant words or filler.

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

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

For a simple two-parameter tool with no output schema, the description covers the core purpose, the overwrite behavior, and the required inputs. It lacks details on return values or error behavior, but the tool's simplicity and the mock-file-system context make it reasonably complete.

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

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

The input schema covers both parameters fully (100% coverage) with descriptions for path and content. The description's instruction to 'Specify the full path and content' adds minimal value beyond the schema, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool's function: 'Creates or overwrites a file in the mock file system.' It uses a specific verb and resource, and distinguishes itself from siblings like read_file and list_files by focusing on file creation/overwrite.

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

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

The description implies when to use the tool (when creating or overwriting a file), but it does not explicitly mention when not to use it or provide alternatives. It's clear enough for the simple use case, but lacks the explicit context and exclusions seen in high-scoring examples.

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