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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Stage files' implies a mutation operation (adding files to the staging area), but it doesn't describe what staging entails (e.g., preparing files for commit), whether it's reversible (e.g., via git reset), or any side effects (e.g., changes to the git index). For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is extremely concise with just two words ('Stage files'), which is front-loaded and wastes no space. Every word earns its place by directly conveying the core action and target. This is optimal for a simple tool where the name and parameters provide additional context.

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

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

Given the complexity of a git staging operation (a mutation with no annotations and no output schema), the description is incomplete. It doesn't explain what staging does in git terms, what the expected outcome is, or any error conditions (e.g., invalid paths). For a tool that modifies repository state, more context is needed to guide the agent effectively.

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

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

The schema description coverage is 100%, with clear descriptions for both parameters ('files' and 'path'), including format requirements (absolute paths). The description 'Stage files' implies the 'files' parameter but adds no additional semantic meaning beyond what the schema provides (e.g., it doesn't explain what types of files can be staged or how wildcards might work). Baseline 3 is appropriate since the schema does the heavy lifting.

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

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

The description 'Stage files' clearly states the verb ('stage') and resource ('files'), making the purpose immediately understandable. It distinguishes from siblings like commit, push, or stash_save by focusing specifically on staging rather than committing, pushing, or stashing operations. However, it doesn't explicitly differentiate from all siblings (e.g., it could be more specific about what staging entails versus other git 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 doesn't mention prerequisites (e.g., needing a git repository), when staging is appropriate (e.g., before committing), or what alternatives exist (e.g., using commit directly for unstaged files). This lack of context leaves the agent to infer usage from the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Create a new branch' implies a write operation, but it doesn't disclose critical traits like whether it requires specific permissions, what happens on conflicts (e.g., if the branch exists), side effects (e.g., modifying repository state), or error conditions. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is a single, efficient sentence with zero waste—'Create a new branch' directly conveys the core action without fluff. It's appropriately sized for a simple tool and front-loaded with the essential information, making it easy to parse quickly. Every word earns its place by specifying the verb and resource.

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

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

Given the complexity of a branch creation tool (a mutation operation with 5 parameters) and no annotations or output schema, the description is incomplete. It lacks information on behavioral traits (e.g., error handling, side effects), usage context (e.g., repository requirements), and output details (e.g., success confirmation or branch details). For a tool that modifies system state, this minimal description is inadequate to ensure safe and correct use.

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

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

Schema description coverage is 100%, with all 5 parameters well-documented in the input schema (e.g., 'force' allows overriding existing branches, 'path' specifies repository location). The description adds no parameter information beyond what the schema provides, not even hinting at required parameters like 'name'. Since the schema does the heavy lifting, the baseline score of 3 is appropriate, but no extra credit is earned.

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 'Create a new branch' clearly states the verb ('Create') and resource ('branch'), making the purpose immediately understandable. It distinguishes this tool from siblings like branch_delete, branch_list, tag_create, etc., which perform different operations on branches or other resources. However, it doesn't specify what type of branch (e.g., Git branch) or provide additional context like the repository scope, which prevents a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing repository), compare it to similar tools like checkout (which might create branches in some contexts), or indicate scenarios where it's appropriate (e.g., starting new features). Without such context, users must infer usage from the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Delete' implies a destructive, irreversible mutation, but the description doesn't specify consequences (e.g., data loss, inability to undo), permissions required, or error conditions (e.g., if the branch doesn't exist). This is inadequate for a mutation tool with zero annotation coverage.

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

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

The description is extremely concise with just three words, front-loading the core action. There is zero waste or redundancy, making it easy to parse quickly. However, this conciseness comes at the cost of completeness, as noted in other dimensions.

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 (destructive mutation with 2 parameters) and lack of annotations and output schema, the description is incomplete. It doesn't cover behavioral aspects like safety, return values, or error handling. For a delete operation, this gap could lead to misuse by an agent, making it inadequate overall.

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

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

Schema description coverage is 100%, with clear descriptions for both parameters ('name' and 'path'), so the schema does the heavy lifting. The description adds no additional meaning about parameters beyond what's in the schema, such as format examples or constraints. Baseline 3 is appropriate as the schema provides sufficient 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 'Delete a branch' clearly states the verb ('Delete') and resource ('a branch'), making the tool's purpose immediately understandable. It distinguishes from siblings like 'branch_create' or 'branch_list' by specifying the destructive action. However, it doesn't explicitly mention the repository context, which is implied but could be more specific.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., ensure the branch isn't currently checked out), exclusions (e.g., cannot delete protected branches), or related tools like 'tag_delete' for similar operations. Without such context, an agent might misuse 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'List all branches' implies a read-only operation but does not specify output format (e.g., list of names, details), pagination, sorting, or error handling (e.g., if the path is invalid). It lacks details on permissions, rate limits, or whether it includes remote branches, leaving significant gaps in transparency.

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

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

The description is extremely concise with just three words, front-loading the core action ('List all branches') without any unnecessary elaboration. Every word earns its place by directly conveying the tool's purpose, making it efficient and well-structured for quick understanding.

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

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

Given the lack of annotations and output schema, the description is incomplete for a tool that interacts with a repository. It does not explain what 'branches' entails (e.g., local, remote, current), the return format, or error conditions. For a tool with one parameter and no structured output, more context is needed to guide effective use, especially among siblings like 'tag_list'.

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

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

The input schema has 100% description coverage for its single parameter ('path'), so the description does not need to add parameter details. The description does not mention the 'path' parameter or provide any additional semantic context beyond what the schema offers. This meets the baseline for high schema coverage but adds no extra value.

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

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

The description 'List all branches' clearly states the verb ('List') and resource ('branches'), making the purpose understandable. However, it lacks specificity about scope (e.g., local vs. remote branches) and does not distinguish itself from sibling tools like 'tag_list' or 'remote_list', which follow a similar pattern. This makes it adequate but vague in differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., requiring a repository path), exclusions, or comparisons to siblings like 'status' (which might show branch info) or 'remote_list' (for remote branches). Without such context, users must infer usage from the tool name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions execution 'in sequence' and that it's 'preferred' for multiple operations, but lacks critical details: it doesn't specify error handling (e.g., whether failures stop the sequence), authentication needs, rate limits, or what happens if the repository path is invalid. For a tool that performs multiple Git operations, this is a significant gap in transparency.

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

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

The description is appropriately sized and front-loaded: two concise sentences that directly state the purpose and usage guidance. Every sentence earns its place with zero waste, making it easy for an AI agent to parse quickly and understand the core functionality.

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

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

Given the complexity (multiple Git operations), no annotations, and no output schema, the description is moderately complete but has gaps. It covers the high-level purpose and usage context but lacks behavioral details (e.g., error handling) and output expectations. For a tool with 2 parameters and rich nested actions in the schema, more context on execution behavior would improve completeness.

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

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

Schema description coverage is 100%, so the schema already documents both parameters ('actions' and 'path') thoroughly. The description adds no additional parameter semantics beyond what's in the schema—it doesn't explain parameter interactions, constraints, or examples. Baseline 3 is appropriate when the schema does the heavy lifting, but the description doesn't compensate or add value here.

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

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

The description clearly states the tool's purpose: 'Execute multiple Git operations in sequence.' It specifies the verb ('execute') and resource ('Git operations'), though it doesn't explicitly distinguish from siblings like 'commit' or 'push' which handle single operations. The 'preferred way' phrase hints at differentiation but isn't specific about sibling relationships.

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

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

The description provides clear context for usage: 'This is the preferred way to execute multiple operations.' This implicitly guides when to use this tool (for multiple operations) versus alternatives (single-operation tools like 'commit' or 'push'), though it doesn't explicitly name alternatives or state when not to use it. The guidance is helpful but could be more explicit about sibling tool comparisons.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the action ('switch' and 'restore') but doesn't clarify critical aspects like whether this is a destructive operation, what permissions are needed, how errors are handled, or what the output looks like. For a tool that modifies repository state, this is a significant gap.

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

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

The description is extremely concise with a single, clear phrase that front-loads the core functionality. Every word earns its place, avoiding redundancy or unnecessary elaboration, making it easy for an agent to parse quickly.

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

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

Given the complexity of a Git checkout operation (which can change branch state or overwrite files), the description is insufficient. With no annotations and no output schema, it fails to address safety concerns, error conditions, or return values. For a tool with potential destructive effects, more context is needed to ensure correct usage.

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

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

Schema description coverage is 100%, so the input schema fully documents both parameters ('path' and 'target'). The description adds no additional semantic context beyond what's in the schema, such as examples of valid 'target' values or interactions between parameters. This meets the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose with specific verbs ('switch branches' and 'restore working tree files'), making it immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'branch_create' or 'stash_pop' that might also involve branch or file 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 like 'branch_create' for creating branches or 'stash_pop' for restoring files. It lacks context about prerequisites, typical scenarios, or exclusions, leaving the agent to infer usage from the purpose alone.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. 'Clone a repository' implies a read operation that creates a local copy, but it doesn't specify whether this requires network access, authentication, or has side effects like creating directories. It lacks details on error handling, success criteria, or what happens if the path exists, leaving significant gaps for a mutation-like 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, efficient sentence with zero wasted words. It is front-loaded with the core action and resource, making it immediately scannable. Every word ('clone', 'a', 'repository') earns its place by contributing essential meaning 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?

Given the complexity of a cloning operation (involving network access, file system changes, potential authentication), the description is incomplete. With no annotations and no output schema, it fails to address critical aspects like what the tool returns (e.g., success message, error details), behavioral traits, or usage context. This is inadequate for a tool that likely performs significant operations.

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

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

Schema description coverage is 100%, with both parameters ('path' and 'url') well-documented in the schema itself. The description adds no additional parameter semantics beyond implying that 'url' is for the source repository and 'path' is the destination. This meets the baseline score of 3 since the schema does the heavy lifting.

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

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

The description clearly states the action ('clone') and resource ('a repository'), making the purpose immediately understandable. It distinguishes this tool from siblings like 'init' (create new repo) or 'pull' (update existing repo). However, it doesn't specify what type of repository (e.g., Git) or mention the cloning mechanism, which prevents a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing Git installed), contrast with 'init' for creating new repos, or specify when cloning is appropriate versus other operations like 'pull' for existing repos. The agent must infer usage from context alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Create a commit' implies a write operation but doesn't specify permissions needed, whether it's destructive to existing data, error conditions, or what happens on success. This is a significant gap for a mutation tool.

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

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

The description is extremely concise with just three words, front-loaded and zero waste. It efficiently states the core action without unnecessary elaboration, though this brevity contributes to gaps in other dimensions.

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

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

Given the complexity of a commit operation (a mutation with no annotations or output schema), the description is incomplete. It lacks details on behavioral traits, usage context, and expected outcomes, making it inadequate for an AI agent to reliably invoke this tool without additional inference.

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

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

Schema description coverage is 100%, so the schema already documents both parameters ('message' and 'path') adequately. The description adds no additional meaning beyond what the schema provides, such as explaining the commit message format or path requirements, meeting the baseline for high schema coverage.

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

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

The description 'Create a commit' states the action (create) and resource (commit), which is clear but basic. It doesn't differentiate from sibling tools like 'add' or 'push', which could also be involved in commit workflows, making it somewhat vague in isolation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing staged changes), exclusions, or relationships with siblings like 'add' or 'push', leaving usage context implied at best.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. While 'Initialize' implies a write operation, it doesn't specify what exactly gets created (.git directory, initial commit), whether it overwrites existing repositories, or what permissions are required. This leaves significant behavioral gaps.

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

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

The description is a single, efficient sentence that states the core purpose without any wasted words. It's appropriately sized for a simple tool and front-loads the essential information.

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

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

For a single-parameter tool with good schema coverage but no annotations or output schema, the description provides the basic purpose but lacks behavioral context about what initialization entails. It's minimally adequate but leaves important questions unanswered about the tool's effects.

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 100% description coverage for its single parameter, so the baseline is 3. The description doesn't add any parameter-specific information beyond what's already in the schema, but it doesn't need to compensate for gaps either.

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 ('Initialize') and resource ('a new Git repository'), making the purpose immediately understandable. However, it doesn't explicitly differentiate from sibling tools like 'clone' (which also creates repositories), so it doesn't reach the highest score.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'clone' (for existing repositories) or prerequisites for initialization. It simply states what the tool does without contextual usage information.

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

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

With no annotations provided, the description carries full burden but offers minimal behavioral insight. 'Pull changes from remote' implies a read/write operation that merges remote changes into the local branch, but it doesn't disclose critical behaviors like: whether it requires network connectivity, what happens on conflicts, if it modifies the working directory, or authentication needs. This is inadequate for a mutation tool with zero annotation coverage.

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

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

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core purpose and appropriately sized for a tool with good schema coverage.

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 Git pull operation with 3 parameters, no annotations, and no output schema, the description is incomplete. It lacks information about what the tool returns (e.g., success/failure, merge results), error conditions, side effects, or typical workflow context. This leaves significant gaps for an agent to use it correctly.

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

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

Schema description coverage is 100%, so parameters are well-documented in the schema itself. The description adds no parameter-specific information beyond what's in the schema (e.g., it doesn't explain the relationship between branch, path, and remote, or typical values). Baseline 3 is appropriate when the schema handles parameter documentation.

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

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

The description 'Pull changes from remote' clearly states the action (pull) and target (changes from remote), which is specific to Git operations. It distinguishes from siblings like 'push' (which sends changes) and 'clone' (which copies entire repository), but doesn't explicitly differentiate from similar tools like 'fetch' (not in sibling 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 no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing repository with a remote configured), when not to use it, or how it compares to similar Git operations like 'fetch' (which retrieves changes without merging).

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Push commits to remote' implies a write operation that modifies remote repositories, but it doesn't disclose critical behaviors like potential overwriting of remote changes (implied by 'force'), authentication needs, error conditions (e.g., if the branch doesn't exist), or side effects. This leaves significant gaps for safe and effective use.

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

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

The description is a single, efficient phrase ('Push commits to remote') that front-loads the core purpose without unnecessary words. Every word earns its place, making it easy to parse quickly. There's no redundancy or fluff, which is ideal for 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 the tool's complexity (6 parameters, no annotations, no output schema), the description is incomplete. It doesn't address behavioral aspects like mutation effects, error handling, or output expectations, which are crucial for a tool that modifies remote state. The high schema coverage helps with parameters, but overall context for safe invocation is lacking.

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

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

The schema description coverage is 100%, with all parameters well-documented in the schema (e.g., 'branch' as branch name, 'force' to force push changes). The description adds no additional parameter semantics beyond what's in the schema, such as explaining interactions between parameters (e.g., using 'force' with 'branch'). Given the high schema coverage, the baseline score of 3 is appropriate.

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

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

The description 'Push commits to remote' clearly states the verb ('push') and resource ('commits to remote'), making the purpose immediately understandable. It distinguishes this from sibling tools like 'pull', 'commit', or 'clone', which have different operations. However, it doesn't specify what kind of commits (e.g., local commits) or mention the repository context, which prevents a perfect score.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., having commits ready to push), when to use 'force' or 'noVerify' options, or differentiate from similar tools like 'pull' for fetching changes. Without such context, the agent must infer usage from the tool name alone.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'Add a remote' implies a write/mutation operation, but it doesn't specify whether this requires specific permissions, what happens on success/failure, if it's idempotent, or any side effects. For a mutation tool with zero annotation coverage, this is a significant gap in transparency.

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

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

The description is extremely concise with a single phrase 'Add a remote', which is front-loaded and wastes no words. While it may be under-specified, it's not verbose or poorly structured—every word earns its place by stating 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?

Given this is a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what a 'remote' is in context, what the tool returns, error conditions, or how it interacts with sibling tools. For a 3-parameter tool that modifies state, more context is needed to be fully helpful to an agent.

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

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

Schema description coverage is 100%, with clear descriptions for all three parameters (name, path, url). The description adds no additional parameter semantics beyond what the schema already provides, such as explaining relationships between parameters or usage examples. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description 'Add a remote' is a tautology that restates the tool name without specifying what a 'remote' is or what resource it operates on. While it implies a Git repository context from sibling tools, it doesn't distinguish this tool from other remote-related tools like 'remote_list' or 'remote_remove' beyond the basic verb. It's minimally better than just 'Process' but still vague about purpose.

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 'remote_list' or 'remote_remove', nor any prerequisites or context for adding a remote. The description doesn't mention when this operation is appropriate or what scenarios it addresses, leaving usage entirely to inference from the tool name and sibling list.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'List remotes' gives no information about output format (e.g., structured list vs. raw text), error conditions (e.g., invalid repository path), side effects (none expected for listing), or performance characteristics. This is inadequate for a tool with even basic functionality.

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

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

The description is maximally concise at two words with no wasted text. It's front-loaded with the core action ('List remotes') and contains no unnecessary elaboration. While under-specified, it achieves perfect conciseness within its limited scope.

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

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

Given the tool's moderate complexity (Git operation with one parameter) and absence of both annotations and output schema, the description is incomplete. It fails to explain what 'remotes' are in Git context, what information is returned, or how this tool fits within the Git workflow alongside siblings like 'remote_add' and 'push'. The agent would struggle to use this effectively.

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

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

The description adds no parameter information beyond what the schema provides. However, schema description coverage is 100% (the 'path' parameter is fully documented in the schema), and there's only one optional parameter. This meets the baseline of 3 where the schema does the heavy lifting, though the description contributes zero additional 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 'List remotes' is a tautology that restates the tool name 'remote_list' without adding meaningful context. It doesn't specify what 'remotes' are (Git remote repositories) or what information is listed (names, URLs, fetch/push specifications). While the verb 'List' is clear, the resource 'remotes' lacks specificity compared to sibling tools like 'remote_add' or 'remote_remove'.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an initialized Git repository), typical use cases (e.g., checking configured remotes before pushing), or relationships with sibling tools like 'remote_add' for adding remotes or 'clone' for initial remote setup. The agent receives zero contextual direction.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Remove a remote' but doesn't explain what 'remove' entails (e.g., deletion from configuration, irreversible action, permissions required, or error handling). This is inadequate for a mutation tool with zero annotation coverage.

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

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

The description is a single, efficient sentence with zero waste. It's appropriately sized and front-loaded, making it easy to parse without unnecessary elaboration.

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

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

Given the tool's complexity (a mutation operation with no annotations and no output schema), the description is incomplete. It lacks details on behavior, error cases, or what happens upon removal, leaving significant gaps for an agent to understand the tool fully.

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

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

Schema description coverage is 100%, with clear descriptions for both parameters ('name' and 'path'). The description doesn't add any meaning beyond the schema, such as explaining how parameters interact or providing examples. Baseline 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states the action ('Remove') and the resource ('a remote'), which is specific and unambiguous. However, it doesn't distinguish this tool from sibling tools like 'remote_add' or 'remote_list' beyond the verb, missing explicit differentiation.

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

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

No guidance is provided on when to use this tool versus alternatives. For example, it doesn't mention prerequisites (e.g., needing an existing remote) or compare it to sibling tools like 'remote_list' for checking remotes first. This leaves the agent without context for appropriate invocation.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'List stashes' implies a read-only operation, but it doesn't specify what information is returned (e.g., stash IDs, messages, dates), whether it requires Git repository access, or if there are any limitations (e.g., only shows local stashes). This leaves key behavioral traits unclear.

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 'List stashes' is extremely concise at two words, with zero wasted language. It's front-loaded and to the point, making it easy to scan. However, it may be overly terse, risking under-specification, but it earns high marks for efficiency within the conciseness dimension.

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

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

Given the complexity (a Git-related tool with siblings like 'stash_pop'), no annotations, no output schema, and a simple input schema, the description is incomplete. It doesn't explain what 'stashes' are, what the output looks like, or how it fits into the broader toolset. For a tool in a Git context, more context is needed to be fully helpful.

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

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

The input schema has 100% description coverage, with the 'path' parameter well-documented as an absolute path to a repository. The description adds no additional meaning beyond this, as it doesn't mention parameters at all. According to the rules, with high schema coverage (>80%), the baseline is 3, which is appropriate here since the schema does the heavy lifting.

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

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

The description 'List stashes' clearly states the verb ('List') and resource ('stashes'), making the basic purpose understandable. However, it lacks specificity about what 'stashes' are in this context (e.g., Git stashes) and doesn't distinguish it from sibling tools like 'stash_pop' or 'stash_save', which are related but different operations. This makes it vague in differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a repository path), exclusions, or comparisons to siblings like 'stash_pop' (which retrieves stashes) or 'status' (which might show stash status). Without such context, users must 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?

With no annotations provided, the description carries full burden for behavioral disclosure. 'Apply and remove a stash' implies a destructive operation (removing the stash after applying), but it doesn't clarify critical behaviors: whether this requires a clean working directory, what happens if conflicts occur during application, whether the operation is reversible, or what the typical output/confirmation looks like. The description is too minimal for a mutation tool.

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

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

The description is extremely concise at just three words ('Apply and remove a stash'), with zero wasted words. It's front-loaded with the core action and resource. While it may be too brief for completeness, it earns full marks for 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 this is a destructive mutation tool with no annotations and no output schema, the description is insufficiently complete. It should explain more about the behavioral implications (conflict handling, irreversibility), typical usage patterns, and what to expect after execution. The current description leaves too many open questions for safe and effective use.

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

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

Schema description coverage is 100%, with both parameters ('index' and 'path') well-documented in the schema. The description adds no additional parameter semantics beyond what the schema already provides (e.g., it doesn't explain what 'stash index' means in practice or provide examples of when to use index vs default). This meets the baseline for high schema coverage.

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

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

The description 'Apply and remove a stash' clearly states the action (apply and remove) and resource (a stash), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'stash_list' or 'stash_save', which would require more specific language about this being a destructive operation that both applies stash changes and deletes the stash.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention when to choose 'stash_pop' over 'stash_list' (for viewing) or 'stash_save' (for creating), nor does it specify prerequisites like having stashes available or being in a git repository context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states 'Save changes to stash' but doesn't explain what happens to the working directory after saving (e.g., whether changes are removed or kept), authentication needs, error conditions, or side effects. This leaves critical behavioral traits undocumented for a mutation tool.

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

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

The description is extremely concise with a single sentence 'Save changes to stash', which is front-loaded and wastes no words. Every part of the sentence contributes to understanding the tool's purpose, making it efficient and easy to parse.

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

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

Given the complexity of a Git stash operation (mutating state with multiple parameters) and no annotations or output schema, the description is incomplete. It lacks details on behavior, return values, error handling, and how it interacts with sibling tools like 'stash_pop'. For a tool with 5 parameters and no structured safety hints, more context is needed.

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

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

Schema description coverage is 100%, so the schema fully documents all 5 parameters. The description doesn't add any parameter-specific details beyond what the schema provides, but with high coverage, a baseline of 3 is appropriate. Since no parameters are required, the description's simplicity aligns well, earning a slightly higher score for not overcomplicating.

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 'Save changes to stash' clearly indicates the action (save) and target (stash), but it's somewhat vague about what 'changes' specifically refers to (e.g., uncommitted modifications). It doesn't differentiate from sibling tools like 'stash_list' or 'stash_pop', which describe listing or applying stashed changes, leaving room for ambiguity in tool selection.

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

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

No explicit guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing uncommitted changes), exclusions, or compare to siblings like 'commit' for saving changes permanently. The description implies usage for saving changes temporarily, but 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?

With no annotations provided, the description carries full burden for behavioral disclosure but offers minimal information. It doesn't specify what data is returned (e.g., file changes, branch state), whether it's read-only (implied but not stated), performance characteristics, or error conditions. The description merely restates the action without behavioral 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 extremely concise at just three words ('Get repository status'), with zero wasted language. It's front-loaded with the core action and resource. Every word earns its place, making it efficient for quick understanding.

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

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

Given the tool's moderate complexity (repository status can involve multiple data types) and the absence of both annotations and output schema, the description is insufficiently complete. It doesn't explain what 'status' includes, the return format, or error handling. For a tool with no structured output documentation, the description should provide more context about what information is retrieved.

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 100% description coverage for its single parameter ('path'), so the description doesn't need to add parameter details. The description doesn't mention the 'path' parameter at all, which is acceptable since the schema fully documents it. This meets the baseline for high schema coverage.

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

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

The description 'Get repository status' clearly states the verb ('Get') and resource ('repository status'), making the tool's purpose immediately understandable. However, it doesn't differentiate this from sibling tools like 'stash_list' or 'tag_list' which also retrieve status information about different repository aspects, so it doesn't achieve full sibling differentiation.

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

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

The description provides no guidance on when to use this tool versus alternatives. There's no mention of what 'repository status' includes (e.g., staged/unstaged changes, branch info) or when to choose this over other status-related tools like 'stash_list' or 'branch_list'. The agent must infer usage from the tool name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. 'Create a tag' implies a write operation, but it doesn't mention permissions needed, whether creation is reversible, potential side effects (e.g., overwriting with force), or what happens on success/failure. This is insufficient for a mutation tool with zero annotation coverage.

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

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

The description is extremely concise with just two words ('Create a tag'), which is front-loaded and wastes no space. For a tool with a clear name and comprehensive schema, this brevity is appropriate and efficient, earning full marks for 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 the complexity (a mutation tool with 6 parameters) and lack of annotations and output schema, the description is incomplete. It doesn't explain the tool's behavior, return values, or usage context, leaving significant gaps that could hinder an AI agent's ability to invoke it correctly without relying heavily on the schema alone.

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

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

Schema description coverage is 100%, so the schema fully documents all 6 parameters (e.g., 'path' as absolute repository path, 'force' to override existing tags). The description adds no parameter information beyond what's in the schema, but the high coverage justifies a baseline score of 3, as the schema adequately compensates.

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 'Create a tag' clearly states the action (create) and resource (tag), which is adequate. However, it doesn't distinguish this from sibling tools like 'tag_list' or 'tag_delete' beyond the basic verb, nor does it specify what kind of tag (e.g., Git tag) or context, leaving it somewhat vague.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a repository path), when not to use it (e.g., if a tag already exists without force), or refer to sibling tools like 'tag_list' for checking existing tags. This lack of context makes usage unclear.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. 'Delete a tag' implies a destructive mutation, but it doesn't specify whether deletion is permanent, requires specific permissions, has side effects, or provides confirmation. For a destructive tool with zero annotation coverage, this leaves critical behavioral traits undisclosed.

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

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

The description is extremely concise—three words—with zero wasted language. It's front-loaded with the core action and resource. Every word earns its place, making it efficient for quick comprehension.

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

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

Given this is a destructive tool with no annotations and no output schema, the description is incomplete. It doesn't address safety considerations, error conditions, or what happens post-deletion. For a tool that permanently removes data, more context is needed to guide safe usage.

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

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

Schema description coverage is 100%, with both parameters ('name' and 'path') well-documented in the schema. The description adds no parameter semantics beyond what the schema provides—it doesn't explain format constraints, examples, or relationships between parameters. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description 'Delete a tag' clearly states the verb (delete) and resource (tag), making the purpose immediately understandable. It distinguishes from sibling tools like 'tag_create' and 'tag_list' by specifying the destructive action. However, it doesn't specify what kind of tag (e.g., Git tag) or provide additional context about the resource being deleted.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., tag must exist), when not to use it (e.g., if tag is referenced elsewhere), or direct alternatives among siblings. The agent must infer usage from the tool name alone.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'List tags' implies a read-only operation, but it doesn't specify whether it requires a valid repository, what happens if the path is invalid, or the format of the output (e.g., list of tag names). This leaves significant gaps in understanding the tool's behavior.

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

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

The description is extremely concise with just two words ('List tags'), which efficiently conveys the core action and resource without any wasted words. It is front-loaded and appropriately sized 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 the tool's moderate complexity (a list operation with one parameter), lack of annotations, and no output schema, the description is incomplete. It doesn't explain the return values, error conditions, or behavioral nuances, leaving the agent with insufficient context to use the tool effectively beyond basic inference.

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

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

The input schema has 100% description coverage for its single parameter ('path'), so the schema already documents it well. The description adds no additional meaning about parameters beyond what the schema provides, such as clarifying the 'path' usage or default behavior when omitted. Baseline 3 is appropriate given high schema coverage.

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

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

The description 'List tags' clearly states the verb ('List') and resource ('tags'), making the basic purpose understandable. However, it lacks specificity about what kind of tags (e.g., Git tags) and doesn't distinguish from sibling tools like 'tag_create' or 'tag_delete' beyond the obvious list vs. create/delete distinction.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing a Git repository), exclusions, or context for choosing it over other tag-related tools like 'tag_create' or 'tag_delete'.

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