ChatGPT2LocalBridge

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

Annotations already declare readOnlyHint=true, so the read-only nature is clear. The description adds context about the data being 'recent' and covering 'audit events,' but does not go beyond what annotations provide in terms of safety 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 two sentences, front-loaded with the core function and followed by a practical use case. Every word earns its place.

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 differentiates the tool from siblings and is adequate given the output schema exists. However, the lack of parameter documentation reduces completeness for a tool with only two optional 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 0%, yet the tool description does not explain the parameters (limit, includeAudit) or their effects. This leaves the agent without guidance on how to use these 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 clearly states the tool reads 'recent local bridge tool-call records and audit events' and provides a concrete use case: 'inspect what ChatGPT actually asked the MCP server to do.' This distinguishes it from sibling bridge tools like health, logs, and status.

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 implicitly tells when to use the tool (to inspect tool-call records) but does not explicitly mention when not to use it or compare with alternatives. However, the context provided is sufficient for an agent to select it appropriately.

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 the readOnlyHint and openWorldHint annotations, indicating a read operation that may access external endpoints. However, it does not elaborate on potential side effects, latency, or error conditions beyond what annotations imply.

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

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

The description is a single, clear sentence with no unnecessary words. It is appropriately front-loaded but lacks supporting details that could improve usability.

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 for a tool with three undocumented parameters and no output schema details. It omits information about default behavior, success/failure indicators, and usage nuances.

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 the parameters (includePublic, publicBaseUrl, timeoutMs) beyond the schema defaults. With 0% schema description coverage, the description fails to add meaningful guidance on parameter usage or behavior.

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 ('Check') and the resource ('local and optional public bridge health endpoints'). It is specific and distinguishes from sibling tools like bridge.activity, bridge.logs, and bridge.status.

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

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

The description does not provide any guidance on when to use this tool versus alternatives, such as bridge.status or other health check tools. No context is given for appropriate usage scenarios 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 declare readOnlyHint=true, confirming a safe read operation. The description adds 'recent' and 'configured log directory' but does not disclose behaviors like line limits, file selection, or error handling. With annotations covering the safety profile, the description provides modest additional context.

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

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

The description is a single sentence of 13 words, front-loaded with the key action and resource. Every word contributes value, making it highly concise and efficient.

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 (2 optional parameters, read-only annotation, output schema present), the description covers the core functionality sufficiently. It does not explain return values, but that is handled by the output schema. Minor gap: no mention that logs are tail-based, but defaults hint at it.

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

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

Schema description coverage is 0%, so the description should explain the parameters. It mentions 'recent' implying the 'lines' parameter controls count, but does not explicitly describe 'files' or 'lines'. The enum values for files are self-explanatory, but the description fails to add meaningful semantics beyond defaults.

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 'Read' and the resource 'bridge and tunnel log lines', specifying 'recent' and 'from the configured log directory'. This distinguishes it from sibling tools like bridge.activity or bridge.health which provide different data.

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

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

The description provides no guidance on when to use this tool versus alternatives (e.g., code.read, bridge.status). It does not mention context or exclusions, leaving the agent to infer 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, and the description adds context about the scope (bridge and tunnel), but does not elaborate on behavior beyond that.

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

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

Single, concise sentence that front-loads the key information with no redundant text.

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

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

For a zero-parameter, read-only tool with an output schema, the description is sufficiently complete to convey its function.

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?

No parameters exist, so baseline 4; the description correctly states the purpose without needing parameter details.

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 specifies the verb 'Return' and the resource 'local bridge and tunnel launchd service status', clearly distinguishing it from siblings like bridge.health and bridge.logs.

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 checking service status but provides no explicit guidance on when to use it versus 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?

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description adds value by mentioning 'approved local workspace' and syncing context. However, it does not elaborate on overwrite behavior, sha256 verification, or maxBytes limits, leaving gaps for a write tool with open world access.

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

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

The description is two concise sentences, front-loaded with the core action and usage context. Every sentence adds value without 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?

Despite having 6 parameters (3 required), an output schema, and open-world access, the description minimally covers the tool's behavior. It omits details on parameter usage, error handling, and output format, making it incomplete 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?

The description does not mention any of the 6 parameters (projectPath, url, file, overwrite, maxBytes, expectedSha256) or their roles. With 0% schema description coverage, the agent must infer from names and schema types alone, 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 it downloads an HTTPS file URL to a local workspace, specifying the source as 'ChatGPT/App-provided'. This distinguishes it from sibling tools like file.write (which writes content directly) and no other download tool exists among siblings.

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

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

The description explicitly says 'Use this when a cloud-side file has a download link and should be synced to local disk.' This provides clear context for when to use, though it does not explicitly mention when not to use or list 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?

Annotations already declare readOnlyHint=true, so the tool's safety is clear. The description adds that it reads 'text files' but does not disclose other behavioral traits (e.g., encoding, handling of missing files, line limits beyond schema defaults). With annotations covering the primary behavioral concern, a 3 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 a single concise sentence that front-loads the primary purpose. However, it sacrifices necessary detail for brevity. Still, it earns a 4 due to efficient structure.

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 existence of an output schema and 3 parameters with 0% schema coverage, the description should compensate by explaining parameter usage and return behavior. It fails to do so, leaving the agent with significant gaps. The completeness is inadequate for safe and 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?

The description does not clarify the meaning of any parameter. Schema description coverage is 0%, so the burden on description is high. An agent cannot infer what 'projectPath' should be (absolute/relative path?) or how 'files' should be specified (relative to projectPath?). The maxLines parameter is also unexplained despite having a default and bounds.

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 ('Read'), resource ('text files'), and scope ('from a local project'). It distinguishes from siblings like code.read_range and code.search by focusing on full files, not ranges or search results.

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 code.read_range or code.search. No explicit context or exclusion criteria are mentioned.

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, indicating a safe read operation. The description adds that it reads a bounded line range, which is the key behavioral trait. However, it does not disclose edge cases like what happens if startLine > endLine or if the file doesn't exist.

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

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

Single clear sentence that efficiently conveys the tool's purpose with no extraneous words. 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?

The description is minimal and leaves out usage guidelines and parameter details. Given that there is an output schema (reducing need to explain return values) and 4 required parameters, the description could provide more context about the range parameters or file path format.

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 has 0% description coverage for parameters. The description implies that 'startLine' and 'endLine' define the range via 'bounded line range', but provides no additional meaning for 'projectPath' or 'file'. Baseline 3 is appropriate as it adds partial 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?

Description explicitly states 'Read a bounded line range from one text file inside a project.' It specifies the verb 'read' and the precise resource (bounded line range, one text file), distinguishing it from siblings like 'code.read' (reads whole file) and 'code.search' (searches content).

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. For example, it does not mention that reading the entire file should use 'code.read', or that searching across files should use 'code.search'. Missing 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 readOnlyHint=true, indicating safe read operation. The description adds that output is ripgrep-compatible, providing some behavioral context beyond annotations, but does not detail any other behavioral traits.

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, making it concise but lacking structure. It does not present information in a clear, front-loaded format and could benefit from organizing key 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?

Given the tool has four parameters with no schema descriptions and an output schema exists, the description fails to explain parameter semantics or usage context. It only covers purpose and output format, leaving 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?

Schema description coverage is 0%, and the description does not mention any parameters, their types, or their purpose. The four parameters (projectPath, query, glob, maxResults) remain undocumented, offering no 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 the tool searches local project files and specifies that the output is ripgrep-compatible, providing a specific verb and resource. It distinguishes itself from siblings like code.read and code.read_range which read file content.

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 such as code.read for reading entire files or file.list for listing files. The description does not mention when not to use it or any 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 indicate readOnlyHint=false and destructiveHint=false, so the description does not contradict them. However, it fails to disclose that overwrite is possible (via the overwrite parameter) or what happens if the target file exists. The description adds no 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 a single short sentence, which is concise but too terse given the tool's complexity (4 parameters). It avoids fluff but fails to front-load important 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?

With 4 parameters, an output schema, and multiple sibling tools, the description is incomplete. It does not clarify path formats, the behavior of overwrite, or how copy differs from move. The description lacks enough 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 0%, yet the description offers no explanation of the parameters (projectPath, from, to, overwrite). The description does not compensate for the lack of schema descriptions, leaving parameter semantics entirely unspecified.

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 'Copy a file inside a project' clearly states the verb (copy) and resource (file) and scopes it to a project. It distinguishes from siblings like file.move or file.delete, though lacks any additional 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?

The description provides no guidance on when to use this tool versus alternatives (e.g., file.move, file.write). No prerequisites or context for usage are mentioned.

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. The description adds minimal context beyond 'inside a project', but does not contradict annotations. It lacks details on deletion behavior (e.g., permanence, confirmation prompt).

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, concise and front-loaded. However, some users may desire more detail given the tool's destructive nature.

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 parameter descriptions and an output schema, the description is too minimal. It does not explain return behavior, error cases, or the necessity of the confirm parameter, relying entirely on external 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 coverage is 0%, and the description does not explain any parameter meaning. In particular, the required confirm parameter is not mentioned as needing to be true to proceed, leaving ambiguity.

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 specifies the action (delete) and resource (file), with scope 'inside a project'. It distinguishes itself from sibling tools like file.copy or file.list as the only delete 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 file.delete versus alternatives (e.g., file.patch for modification) or when not to use it. The description does not mention prerequisites or safety considerations.

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?

Description adds context beyond annotations by specifying it lists without reading contents. Annotations already declare readOnlyHint=true and openWorldHint=false, which aligns. No contradictions. However, it does not disclose behavior like recursion limits or performance characteristics, but the annotations cover safety.

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

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

The description is a single sentence that is front-loaded with the key action. Every word is necessary and there is no redundancy or wasted text.

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

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

Given the presence of output schema and annotations, the description provides the basic purpose but lacks details on parameter behavior, error conditions, or example usage. For a tool with 4 parameters and a recursive option, more context about how to use them would improve completeness.

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

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

Schema coverage is 0% (description does not mention any parameters). With 4 parameters, the description fails to add meaning beyond the schema. For example, it does not explain the role of 'projectPath', 'dir', 'recursive', or 'maxEntries'. This is a critical 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 the verb 'List' and the resource 'files and directories inside a project directory', and distinguishes itself from file reading tools by adding 'without reading file contents'. This is specific and differentiates it from siblings like file.read.

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

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

The description implies usage for listing without reading, but does not explicitly mention when to use this tool vs alternatives like file.stat or code.read. No exclusions or alternative suggestions are provided, relying on the agent to infer from sibling names.

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 it is not read-only (readOnlyHint=false) and not destructive (destructiveHint=false), which is consistent. The description says 'Create', implying mutation. However, it does not disclose behavior if the directory already exists, what happens on error, or the effect of the 'recursive' parameter (default true). More transparency is needed.

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, but it is overly terse. While concise, it sacrifices clarity and completeness. A slightly longer description structuring the key aspects would be more helpful.

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 an output schema (not shown) and three parameters, the description is too sparse. It lacks information about error handling, preconditions (e.g., project must exist), return values, or typical usage patterns. The description does not meet the needs of an AI agent selecting between 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 schema has 0% coverage for descriptions, yet the tool description does not explain any of the three parameters (projectPath, dir, recursive). It only says 'inside a project', which vaguely hints at projectPath. This is insufficient for an agent to correctly fill in the 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 clearly states the verb 'Create' and the resource 'directory', and the title reinforces it. It is distinct from sibling file tools (e.g., file.copy, file.delete) because 'mkdir' specifically creates directories, not files or copying. However, it could be more precise about the project context, e.g., 'relative to project root'.

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 file.write (for files) or any prerequisites. The description does not mention situations where mkdir is preferable or any caveats (e.g., directory existence).

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, which are consistent with moving/renaming (mutation but not destructive). The description adds that it works for files and directories, but lacks details on behavior upon overwrite 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?

The description is a single sentence, which is concise but lacks necessary detail. It could be expanded 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?

Given 4 parameters, 3 required, and an output schema, the description is insufficient. It does not mention return values, error cases, or the role of the overwrite parameter.

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

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

Schema description coverage is 0% and the description provides no explanation of parameters (projectPath, from, to, overwrite). It fails to add meaning beyond the schema, e.g., path formats or default behavior.

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 ('Move or rename') and resource ('file or directory'), and specifies the context ('inside a project'). It distinguishes from siblings like file.copy and file.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?

The description provides no guidance on when to use this tool versus alternatives (e.g., file.copy for copying). It does not mention prerequisites, conditions, or limitations.

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?

Adds behavioral detail beyond annotations: fails on zero/multiple matches unless replaceAll. Annotations don't specify this. Could mention that changes are irreversible or require permissions.

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

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

Single sentence, front-loaded action, no wasted words. Highly 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?

Covers core behavior and main condition. Lacks info on return value, error handling beyond the described condition, and performance. But given simplicity, it's mostly complete.

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

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

Schema description coverage is 0%. Only replaceAll is mentioned, while other parameters (projectPath, file, oldText, newText) are not described. Names are self-explanatory, but description should compensate for lack of 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?

Description clearly states the action ('Replace exact text inside a file') and key condition (fails unless exactly one match unless replaceAll). Differentiates from sibling tools like file.write and file.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?

Implied usage for replacing exact text, but no explicit guidance on when to use vs alternatives like file.write or code.search. No when-not conditions 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?

The description adds the optional SHA256 inclusion behavior, which is not in annotations. However, there is no mention of other behavioral aspects like recursion, permissions, or metadata fields. Annotations already indicate read-only, so the description's additional value is moderate.

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, concise and to the point. It is front-loaded with the main action. However, it could be slightly more structured by separating the hash option as an afterthought.

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 presence of an output schema, the return values are covered. However, the description lacks context about projectPath requirements, relative paths, or error conditions. It is adequate but not fully complete for a stat operation.

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

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

Schema description coverage is 0%, and the description does not explain any parameter (e.g., format of projectPath, meaning of includeHash). The agent must infer from parameter names alone, 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 'Return' and the resource 'metadata for a file or directory inside a project', distinguishing it from sibling tools like file.list (listing) or file.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?

The description provides no guidance on when to use this tool versus alternatives such as file.list or file.stat for different purposes. No when-not-to-use or context is given.

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 set destructiveHint=false, but the description describes an overwrite operation, which is inherently destructive. This contradiction undermines transparency. The description adds no clarifying behavioral context 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 two sentences, efficiently conveying the tool's core purpose and a key usage guideline. No unnecessary 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?

The description covers the basic operation but omits details about encoding, size limits, behavior when file exists, or binary file handling. Given the tool has an output schema (presumably documenting returns), it partially compensates but still feels incomplete for nuanced scenarios.

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

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

With 0% schema description coverage, the description should compensate but only offers minimal context. It mentions 'text file' to hint at content type but does not explain the meaning of parameters like projectPath, file, content, or createDirs.

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

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

The description clearly states the tool creates or overwrites a text file inside a project. The verb 'Create or overwrite' combined with the resource 'text file' precisely defines the action, and it distinguishes itself from sibling tools like file.delete, file.copy, etc.

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 advises 'Use code.read first when modifying an existing file,' which provides guidance on when to read before writing. However, it doesn't explicitly state when not to use this tool or suggest alternatives for non-text files.

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 and destructiveHint=false. The description adds that it returns HEAD commit, but does not detail any other behavioral traits like response format or edge cases. With annotations covering safety, a 3 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?

Two sentences, no repetition, front-loaded with the action. Every word serves a purpose.

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

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

For a simple read-only tool with a single parameter and an output schema (not shown but indicated), the description covers the core action and usage pattern. The missing parameter guidance prevents a perfect score.

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

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

The sole parameter 'projectPath' has no description in the schema (coverage 0%), and the description does not mention it at all, leaving the agent to infer its necessity and format without guidance.

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

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

Clearly states 'Return the current HEAD commit' as the primary action. Distinguishes from sibling tools like git.revert and git.status by focusing on capturing a point for potential reversion.

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?

Explicitly advises using 'before a risky edit' and references git.revert as the recovery mechanism, providing clear context for when to invoke 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 already indicate readOnlyHint=true, so the description adds the context of returning 'summary and structured diff'. However, it does not clarify the exact scope (e.g., staged vs unstaged changes, or that ref defaults to HEAD).

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

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

The description is a single sentence that is front-loaded and efficient. It could be slightly more informative about the output structure, but it is not 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 the presence of annotations and an output schema, the description minimally covers the core purpose. However, it omits context about what 'current working tree' means and does not clarify the diff scope (e.g., all changes vs specific files).

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 mention projectPath or provide additional context for the ref parameter beyond what the schema already states. With 50% schema description coverage, the description fails to compensate for the missing parameter descriptions.

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

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

The description clearly states the verb 'Return' and the resource 'git diff summary and structured diff' for the 'current working tree', making the purpose specific and distinguishable from siblings like git.status and git.revert.

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 over alternatives like git.status or git.revert. The description does not mention prerequisites, exclusion criteria, 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 flag destructiveHint=true. The description adds that it restores tracked files and optionally removes untracked files, providing context beyond annotations. However, it does not clarify that the operation is irreversible or requires confirmation.

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

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

Single sentence, no unnecessary words. Clearly front-loaded with 'Destructive' alert.

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, an output schema, and no parameter descriptions, the description is insufficient. It misses details on required confirmation, checkpoint format, and return value.

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

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

With 0% schema description coverage, the description must compensate but only mentions 'checkpoint' and 'cleanUntracked' without explaining them. Parameters like 'confirm' (critical for safety) and 'projectPath' are ignored.

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 ('restore tracked files to a checkpoint') and the resource ('tracked files'), distinguishing it from siblings like git.checkpoint (create) and git.diff (diff).

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. Does not mention prerequisites or conditions (e.g., needing a valid checkpoint).

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=true, so agent knows it's safe. The description adds context about what is returned (branch, HEAD, porcelain status). No additional behavioral details needed for a read-only tool.

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

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

The description is a single, concise sentence with no wasted words. It could be slightly more informative, but 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 tool has one parameter and an output schema, the description is somewhat complete. However, it lacks edge-case handling, such as when the project is not a git repository. Adequate 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?

Schema description coverage is 0%, so the description must compensate. However, it does not explain the meaning or format of the projectPath parameter, leaving the agent to infer its purpose from the name 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 the action (return) and resources (git branch, HEAD, porcelain status). It distinguishes from sibling git tools like git.checkpoint, git.diff, and git.revert which perform different 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?

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, limitations, or exclusions. For a simple status check, usage is implied but not explicit.

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

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

The description discloses that the tool checks listening status and identifies the owning process, adding behavioral context beyond the readOnlyHint annotation. It does not contradict annotations, and it helps the agent understand the tool's capabilities.

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 efficiently conveys the tool's purpose and functionality. Every word contributes meaning, and there is no unnecessary 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 low complexity, the description is complete for a simple check operation. An output schema exists, so return values are not required in the description. It covers the essential behavioral aspects, though mentioning that it operates locally could be beneficial.

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

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

With 0% schema description coverage, the description should compensate by explaining the parameters. It only mentions 'local TCP port' and 'owning process', but does not clarify the host parameter or provide details on how port and host are used. The param names are clear, but the description adds minimal 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 'check', the resource 'local TCP port', and the specific action of checking if it's listening and identifying the owning process. This differentiates it from sibling tools that focus on different resources like files, processes, or cloud services.

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

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

The description does not provide explicit guidance on when to use this tool versus alternatives or when not to use it. However, given the absence of similar port-checking tools among siblings, the purpose is self-explanatory, but a clear distinction would improve the score.

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, so the agent knows this is a safe read operation. The description adds the scope 'started by this bridge runtime', but does not disclose pagination, filtering behavior, or response format beyond what the output schema (if present) might cover.

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 redundancy or irrelevant information. It is front-loaded and efficiently conveys the core function.

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

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

Given the simplicity of the tool (one optional param, output schema present), the description is minimally adequate. However, it lacks details on parameter usage and potential limitations, leaving some gaps in 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 description does not mention the 'workspace' parameter at all, and schema coverage is 0%. For a single optional parameter, the description should at least hint that it serves as a filter, but it provides no additional meaning.

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

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

The description clearly states 'List processes started by this bridge runtime', specifying the action (list) and the resource (processes with a specific scope). It effectively distinguishes from sibling tools like process.start and process.stop.

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 context, prerequisites, or when to prefer process.list over other tools such as bridge.status or shell.exec.

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 openWorldHint=true. The description adds context about persisting pid/log path, but lacks details on blocking, cancellation, or failure 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?

A single short sentence is concise but overly terse. Could benefit from structure like a bullet list or clearer separation of use cases.

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 an output schema existing, the description does not cover prerequisites, side effects, or return behavior. For a tool with 3 parameters and complex behavior, it 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?

Schema description coverage is 0%, and the description adds no explanation for the three parameters (projectPath, command, workspace). The description fails to compensate for 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 clearly states the tool starts a long-running project process and persists its PID and log path. It distinguishes from siblings like process.list and process.stop, though 'project process' could be more precise.

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 shell.exec or process.start vs process.run. No exclusions or prerequisites mentioned.

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 destructive behavior (destructiveHint=true). The description adds that 'confirm=true' is required, which is useful behavioral context 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, with two short sentences that convey all essential information without unnecessary 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 the presence of an output schema and annotations, the description adequately covers the core purpose and a key parameter requirement. It is mostly complete for a simple stop operation, though parameter 'processId' could use a brief explanation.

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

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

With 0% schema description coverage, the description should compensate. It only clarifies that 'confirm' must be true, but provides no explanation for 'processId'. This is insufficient guidance for the two required 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 clearly states the action 'Stop a process' and specifies it is for processes started by 'process.start', differentiating it from siblings like 'process.start' and 'process.list'.

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 requires 'confirm=true', providing a clear usage condition. It implies the tool is for stopping previously started processes, though it does not list 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?

Annotations already specify readOnlyHint=true, so the description adds minimal behavioral context beyond listing return contents. No contradiction. The description does not disclose additional traits like performance 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 one concise sentence that front-loads the main action. However, it omits necessary parameter information, reducing 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 covers the return value with an output schema present, but it ignores the required input parameter. Given one parameter and existing output schema, the description is moderately complete but has a clear 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?

Schema description coverage is 0%, and the description does not mention the 'projectPath' parameter at all, failing to compensate for the lack of schema documentation.

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

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

The description clearly states the tool returns a higher-level project index and lists included items (package scripts, key files, detected tests, top-level structure), but does not explicitly differentiate from sibling tools like project.scripts or project.snapshot.

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 description only describes the output, not 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 declare readOnlyHint=true, so the description's claim of returning data is consistent and adds the specific behavior of reading package.json scripts. However, no behavioral edge cases are disclosed (e.g., missing package.json, invalid path), and the description does not go beyond what the annotations already imply.

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 of only 9 words. It contains no redundancy and is appropriately front-loaded with the key action and object.

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 (one param, safe read, output schema exists), the description is mostly adequate. However, it lacks important context about error handling and preconditions (e.g., project must be Node). The presence of an output schema mitigates the need to explain return values, but overall completeness is average.

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 has 0% description coverage, meaning no parameter documentation in the schema. The description only indirectly hints that 'projectPath' should point to a Node project root, but does not explain the format, constraints, or what happens if the path is invalid. This is insufficient for a required parameter with no 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 uses a specific verb 'Return' and a clear resource 'scripts from package.json for a Node project', making the tool's purpose immediately obvious. It also implicitly distinguishes from sibling tools like 'project.index' or 'project.snapshot' by focusing on a specific file and data type.

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 (e.g., project must be Node-based with a package.json) or situations where it should not be used. The description lacks context for decision-making.

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

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

Annotations already declare the tool as read-only (readOnlyHint: true). The description adds context about the specific data returned (git state, language, etc.) but does not disclose additional behavioral traits such as side effects, permissions, or error states. With good annotation coverage, the description provides marginal 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 concise, consisting of two sentences that front-load the verb and resource. Every sentence adds value without redundancy.

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

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

The tool has a specific purpose, an output schema (so return values are explained there), and the description covers the key components (git state, language, package manager, bounded file tree). No additional 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?

Schema description coverage is 50% (only 'path' has a description; 'maxDepth' has constraints but no description). The description does not add any parameter information beyond what the schema provides. Given moderate 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 the tool's purpose: 'Get local project context: git state, language, package manager, and a bounded file tree.' It uses a specific verb ('Get') and resource ('local project context'), and the detail on what is included (git state, language, package manager, bounded file tree) distinguishes it from sibling tools like 'project.index'.

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 advises when to use the tool: 'Use this before editing a project.' This provides clear context for usage. Although it does not explicitly state when not to use it or list alternatives, the guidance is sufficient for an agent.

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

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

Annotations already indicate destructiveHint=true, and the description adds the mandatory confirm parameter required for execution. This provides behavioral context beyond the annotations, though more detail on what restart entails (e.g., service downtime) is missing.

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 front-load the purpose and immediately follow with the critical usage requirement. No filler or redundancy.

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

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

The description covers the essential aspects: what services, required confirm flag. Since an output schema exists, return values need not be described. It is complete enough for a simple restart operation.

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

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

Despite 0% schema coverage, the description adds meaning to the confirm parameter (must be true) and implies the service parameter's values (bridge, ngrok via enum). It compensates for the lack of schema descriptions.

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

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

The description clearly states the action (restart) and resource (launchd service), listing the two specific services (bridge, ngrok). It effectively distinguishes from sibling tools like bridge.health and bridge.logs by focusing on the restart action.

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 requires confirm=true, which is a critical usage guideline. While it doesn't explicitly contrast with alternatives, the context of siblings (health, logs, etc.) makes it clear when 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 indicate it is not read-only and has open-world effects, but description adds little beyond stating it runs a command. It does not detail potential side effects, security implications, or that commands run in project directory is already implied.

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 succinct sentences with no unnecessary words or structure. Every sentence provides value: purpose and usage contexts.

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 output schema and annotations, the description lacks essential context for a potentially dangerous tool: no details on environment, permissions, error behavior, or safety warnings. 4 parameters with 0% schema coverage are left unexplained.

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

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

Schema description coverage is 0%, and the description does not explain parameters (projectPath, command, timeoutMs, maxOutputBytes). The phrase 'in the project directory' hints at projectPath, but overall 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?

Description explicitly states 'Run a shell command in the project directory and return stdout/stderr', with clear use cases (tests, builds, local inspection). It uniquely identifies the tool among sibling tools that handle files, processes, etc.

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?

Description provides clear contexts: tests, builds, local inspection. However, it does not explicitly state when not to use this tool (e.g., for file operations instead of file.* tools), limiting full guidance.

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

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

Annotations already indicate mutation (readOnlyHint: false). The description adds no further behavioral details (e.g., idempotency, side effects, 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?

The description is concise and front-loaded, but at the cost of omitting important details about parameters and usage. It could include more information 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?

Given the tool has 3 parameters (0% schema coverage) and is a mutation operation, the description lacks essential context about parameter constraints, error handling, and expected behavior. The existence of an output schema does not compensate for missing input guidance.

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

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

Schema description coverage is 0%. The description does not explain the meaning or usage of any parameter (taskId, status, note), even though status has an enum that benefits from clarification.

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 ('Mark'), the resource ('a persisted task/session'), and the possible outcomes ('done or blocked'). It distinguishes from sibling tools like task.start, task.note, and task.status.

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, when not to use it, or any prerequisites. The description is too brief to help with decision-making.

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 a write operation (readOnlyHint=false), but the description adds no further behavioral context, such as whether the note appends to existing notes or if there are 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?

Single sentence is concise and front-loaded, but it may be too brief for optimal clarity given the lack of parameter 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?

With simple parameters and an output schema present, the description still misses usage context and parameter semantics, 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 coverage is 0%, so the description is the only source for parameter meanings. It does not explain 'taskId' (format, validation) or 'note' (content type, length).

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 clearly states the verb 'Append' and the resource 'note to a persisted task/session'. It distinguishes from sibling tools like task.start, task.finish, and task.status, which have 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?

No guidance on when to use this tool vs. alternatives. No mention of prerequisites or context, such as whether the task must already exist or be started.

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 a write operation (readOnlyHint false), and description adds 'lightweight persisted' but no additional behavioral details like side effects, auth needs, or implications. Adequate but not rich.

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

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

Single sentence, 12 words, no redundancy. Concise, though could be more informative without sacrificing conciseness.

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

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

Given 3 parameters and an output schema, the description is minimal. It lacks context on what 'lightweight persisted' entails, how it relates to task.finish, or what the tool returns. Incomplete for guiding agent 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 0%. The description does not explain any parameter meanings. Both the schema and description fail to add semantics beyond parameter names.

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 starts a task/session record, using a specific verb ('Start') and resource. It distinguishes from sibling tools like task.finish and task.note.

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 mention of prerequisites, exclusions, or comparison to sibling tools like task.finish.

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=true, confirming safe read access. The description adds that it can read one or list recent records, but does not elaborate on what 'recent' means or any ordering/pagination behavior beyond the schema's limit parameter.

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

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

Single sentence, front-loaded with action. Efficient but could benefit from a brief note on optional 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?

With an output schema present, return values are covered. However, for a tool with two parameters and no schema descriptions, the description lacks parameter semantics and usage context, making it marginally 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?

Schema description coverage is 0%, so the description must explain parameters. It vaguely implies the optional taskId (for one task) and limit (for list), but does not describe their purpose, syntax, or effects in detail.

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 one task or lists recent task/session records. This specific verb-resource combination distinguishes it from sibling tools like task.finish or task.note which involve mutation.

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. It does not specify that providing taskId retrieves a single task while omitting it lists recent records, nor does it mention any exclusion criteria or alternative tools.

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

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

Annotations already indicate readOnlyHint=true; the description adds 'without running them' reinforcing non-destructive nature, but does not disclose other behavioral traits like heuristics used 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?

Single sentence with 9 words, front-loaded with the action and key differentiator. 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?

Output schema exists (not shown), so return values are covered. However, description lacks detail on what 'detect' entails (heuristics, scope) and the word 'likely' introduces ambiguity. For a simple tool, it's barely 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?

Only one parameter 'projectPath' with 0% schema description coverage. Description does not add any meaning beyond the parameter name (e.g., what path it should point to, required format). Given low coverage, description should compensate but fails.

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 clearly states the action ('detect') and resource ('project test commands') and adds 'without running them' to distinguish from the sibling 'test.run' which executes tests.

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?

Implies use for inspection before running, but lacks explicit guidance on when to use this vs. alternatives like 'project.scripts' or 'shell.exec'. No exclusion criteria or when-not-to-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 minimal behavioral context beyond what annotations provide. Annotations indicate non-read-only and open-world, but the description does not elaborate on side effects, permissions, or execution guarantees.

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 (one sentence) and front-loaded, but its brevity sacrifices informativeness. For a tool with four parameters, it omits essential details, making it under-specified 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?

Given the tool has multiple parameters and an output schema, the description is incomplete. It does not explain input expectations, output format, or usage scenarios, leaving significant gaps in understanding despite the presence of an 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?

With 0% schema description coverage, the description should compensate by explaining parameters. It mentions 'detected or explicit test command' but does not describe 'projectPath', 'command', 'timeoutMs', or 'maxOutputBytes', failing to add meaningful semantic 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 'Run' and the resource 'test command' in a project directory. It distinguishes from sibling 'test.detect' by mentioning 'detected or explicit', making its purpose specific and unambiguous.

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

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

No guidance is provided on when to use this tool versus alternatives like 'test.detect'. There are no exclusions or context cues, leaving the agent to infer usage from the name alone.

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

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

Annotations already indicate readOnlyHint=false (mutable). The description adds no additional behavioral context, such as behavior when name conflicts, whether paths must exist, or side effects. This is insufficient for a write operation.

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

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

The description is a single concise sentence, but it omits necessary details. It is front-loaded but not sufficiently 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 tool's complexity (3 parameters, output schema exists), the description is incomplete. It does not cover parameter descriptions, behavioral expectations, or return value semantics. The presence of an output schema reduces the burden for return value description, but input and behavior are underexplained.

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

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

Schema description coverage is 0%, yet the description does not explain any parameter semantics beyond what parameter names imply. The makeDefault parameter is not mentioned, and the name pattern constraint is not explained.

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 registers a local project path with a workspace name, distinguishing it from sibling tools like workspace.list and workspace.resolve which perform different 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 explicit guidance on when to use this tool versus alternatives. The description implies usage for adding a workspace but does not provide context about prerequisites or cases where alternative tools should be used.

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 readOnlyHint=true, and the description is consistent. However, the description does not add behavioral context beyond what annotations already convey.

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

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

Single sentence, directly to the point with no unnecessary words. Perfectly concise for a simple tool.

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

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

Given zero parameters, an output schema, and simple purpose, the description is complete. No further context 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?

Input schema has no parameters, so schema description coverage is 100%. With zero parameters, the description does not need to provide parameter details; baseline 4 applies.

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

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

The description clearly states the verb 'list' and the resource 'registered local workspaces', distinguishing it from sibling tools like workspace.add and workspace.resolve.

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. The description implies listing is for viewing registered workspaces, but lacks when-not and 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?

The description adds the default behavior beyond the readOnlyHint annotation, and there is no contradiction. It clarifies that the tool is non-destructive and returns a path.

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 fluff. The key information is front-loaded, and every sentence is 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?

For a simple tool with one optional parameter and an output schema, the description covers the main purpose and default case sufficiently.

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 meaning to the single 'name' parameter by indicating it is optional and explaining the behavior when omitted, but does not specify expected format 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 clearly states the verb 'Resolve' and the resource 'workspace name to its project path', which is specific and distinguishes from sibling tools like workspace.add or workspace.list.

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

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

The description provides context for when name is omitted (default workspace) but does not explicitly state when to use this tool over 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.