Server Quality Checklist

Tool Scores

• git_log_repoC
  2.4/5.0
  Behavior2/5

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

  No annotations are provided, so the description must bear full responsibility for behavioral disclosure. It merely says 'Show', which implies a read-only operation, but it does not explicitly state that it is non-destructive, nor does it mention requirements like a valid Git repository, potential side effects, or any limitations on what 'recent' means.

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

  Conciseness2/5

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

  The description is extremely brief, which might be considered efficient, but it omits essential details. It is under-specified rather than appropriately concise—there is no front-loading of critical constraints, and the single sentence provides minimal value beyond the tool name.

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

  Completeness2/5

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

  Given the simplicity of the tool, a one-line description could be sufficient in a richer context, but here the schema and annotations are empty, and no output schema exists. The description fails to cover parameter semantics, expected behavior, or output format, leaving the agent with too little information to invoke the tool correctly.

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

  Parameters1/5

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

  Schema description coverage is 0% (no descriptions in the input schema) and the description does not mention either parameter (repo_path or max_entries). The agent receives no guidance on what these parameters mean, their default values, or how they affect the output. The description fails to compensate for the schema gap.

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

  Purpose4/5

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

  The description states a specific verb and resource: 'Show recent commit history.' This clearly conveys the tool's intent and is not a tautology. It does not explicitly differentiate from sibling tools like git_repo_status or git_diff_repo, but the resource is distinct enough for a capable agent to infer the purpose.

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

  Usage Guidelines2/5

  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 git_repo_status or git_diff_repo. There is no mention of exclusions, prerequisites, or scenarios where this tool is preferred. The agent is left without contextual cues beyond the basic title.

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

• git_commit_repoC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It states the core action (commit) but omits side effects, such as whether it modifies the repository history, requires prior configuration (user.name/email), or how it handles empty commits. The author format hint is the only extra detail, which is insufficient.

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

  Conciseness3/5

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

  The description is brief, which is structurally good, but it sacrifices substance for brevity. It uses two short sentences and front-loads the purpose, but the content is so thin that it fails to earn its place as a useful guide. It is under-specified rather than efficient, so a 3 is appropriate.

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

  Completeness2/5

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

  Given that this is a mutating Git operation with no output schema and no annotations, the description should cover prerequisites (e.g., staged changes, existing repo, user config). It mentions 'staged changes' but omits what the commit will look like, error cases, and any required prior state. The description is incomplete for a tool in this context.

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

  Parameters1/5

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

  Schema description coverage is 0%, so the description must clarify parameters, but it does not. Only the 'author' parameter is given a format hint ('Name <email>'), while 'repo_path' and 'message' are left entirely to the schema's title-only definitions. The description adds almost no value for parameter usage.

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

  Purpose5/5

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

  The description states a clear action ('Commit staged changes') with a specific resource (the repository). It distinguishes itself from siblings like git_stage, git_diff_repo, and git_log_repo by focusing on committing, which is a distinct operation. No ambiguity about what the tool does.

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

  Usage Guidelines3/5

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

  The description implies usage context by mentioning 'staged changes', suggesting it should be used after git_stage, but it does not explicitly state when to use this tool versus alternatives, nor does it mention any prerequisites or competing tools. The guideline is only implicit from the word 'staged'.

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

• git_diff_repoC
  2.9/5.0
  Behavior2/5

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

  With no annotations provided, the description must fully disclose behavior. It doesn't state whether the operation is read-only, whether it modifies state, or what output to expect. It only says 'show the diff', leaving ambiguity about side effects and edge cases.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with zero wasted words. It states the action first and conveys the key distinction efficiently.

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

  Completeness2/5

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

  Despite being a simple tool, the description is incomplete: it doesn't specify the default behavior (staged=false means working tree), explain `repo_path`, or clarify that this is a read-only operation. With no annotations and low schema coverage, more context is needed for an agent to call it correctly.

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

  Parameters3/5

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

  The description explains the `staged` distinction ('working tree or staged changes'), which adds meaning beyond the schema. However, it fails to mention `repo_path` at all, leaving its semantics unexplained. With 0% schema coverage, this partial compensation is insufficient.

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

  Purpose4/5

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

  The description clearly states it 'Shows the diff for a repo's working tree (or staged changes)', using a specific verb and resource. It distinguishes from sibling tools like git_repo_status (status) and git_log_repo (history), though it doesn't name them explicitly.

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

  Usage Guidelines2/5

  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. It doesn't mention exclusions, prerequisites, or situations where another sibling would be more appropriate. An agent must infer usage from the description alone.

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

• git_repo_statusB
  3.2/5.0
  Behavior2/5

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

  With no annotations, the description must carry the burden of behavioral disclosure. It only says 'show', implying read-only, but does not explicitly state non-mutation, no side effects, or any constraints like requiring a valid git repository or permissions. No additional behavioral traits are revealed.

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

  Conciseness5/5

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

  The description is a single, front-loaded sentence with zero waste. It directly states the tool's output scope without filler. Every word contributes to understanding.

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

  Completeness3/5

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

  For a simple status tool, this is adequate but not complete. It tells what it shows but does not describe the return format, error behavior, or how repo_path is used (e.g., defaults to current directory). With no output schema, the agent lacks information about what to expect from the call.

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

  Parameters2/5

  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. It does not mention the repo_path parameter at all, nor its default behavior. While repo_path is self-explanatory from the name, the description adds no meaning beyond the schema, failing to compensate for the lack of schema descriptions.

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

  Purpose5/5

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

  The description clearly states the tool shows staged, unstaged, and untracked files for a repo. This is specific and distinguishes it from siblings like git_diff_repo (differences) and git_log_repo (history). The verb 'show' and resource 'files' are unambiguous.

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

  Usage Guidelines2/5

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

  No mention of when to use this tool versus alternatives. There is no guidance on when to prefer this over other git tools (e.g., git_diff_repo, git_stage) or any prerequisites like 'only use on a valid repo'. The description does not provide context for exclusion.

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

• fs_listA
  3.6/5.0
  Behavior3/5

  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 does reveal that entries are tagged by type, which is useful, but it omits details such as whether hidden files are included, whether the listing is recursive, or any read-only guarantee. For a simple list operation this is 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.

  Conciseness5/5

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

  The description is a single, compact sentence that conveys the core action and output format without any fluff. It is front-loaded and every word earns its place.

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

  Completeness4/5

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

  Given the tool's simplicity (one parameter, no complex schema, no output schema), the description covers the essential behavior and output type. It does not explain error handling or edge cases, but for a listing operation this is sufficient. The lack of annotations and output schema raises the bar, yet the description still provides enough for an agent to call it correctly.

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

  Parameters3/5

  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 elaborate on the 'path' parameter beyond its presence in the schema. However, the parameter is self-explanatory and has a default, so the lack of extra explanation is not a major gap. The description adds no semantic detail but the situation is simple enough that this is acceptable.

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

  Purpose5/5

  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 'entries of a directory', and specifies that each entry is tagged as file or directory. This distinguishes it unambiguously from siblings like fs_read (read file content), fs_write, and fs_search, making the tool's purpose immediately understandable.

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

  Usage Guidelines2/5

  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. It does not mention scenarios where it is preferred (e.g., exploring a directory before reading a file) or when a different tool like fs_search would be more appropriate. The description lacks any routing or exclusionary context.

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

• git_init_repoA
  3.6/5.0
  Behavior2/5

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

  No annotations exist, so the description carries the full burden. It discloses that the tool mutates the filesystem by initializing a repository, but it does not mention side effects such as behavior when the path already exists, permissions needed, or failure modes. This is minimal beyond the obvious action.

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

  Conciseness5/5

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

  A single sentence that immediately states the action and the key parameter nuance. There is zero redundancy, and the most important information is front-loaded.

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

  Completeness4/5

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

  For a simple one-parameter tool with no output schema, the description covers the essential details: what it does and the path base. It could benefit from a note about idempotency or failure but is largely complete given its low complexity.

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

  Parameters3/5

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

  The schema provides no description for repo_path (0% coverage). The tool description compensates by clarifying that the path is relative to FSGUARD_ROOT, which is essential context. However, it does not elaborate on path format, existence requirements, or other constraints, so it only partially compensates for the lacking schema.

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

  Purpose5/5

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

  The description states a clear verb ('Initialize') and a specific resource ('a new git repository at repo_path'), and adds the crucial context that the path is relative to FSGUARD_ROOT. This effectively distinguishes it from sibling git tools like git_repo_status or git_stage, which serve different purposes.

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

  Usage Guidelines3/5

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

  No explicit when-to-use or exclusions are provided. The tool's name and description imply that it is for initializing a repository, while siblings handle other operations, but this is left to inference rather than stated clearly.

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

• fs_readA
  4/5.0
  Behavior3/5

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

  With no annotations, the description must carry the behavioral burden. It correctly implies a read-only operation (no side effects) and adds the key detail that paths are relative to FSGUARD_ROOT. However, it does not disclose error handling, file encoding, or limitation to text files only, which are relevant for safe invocation.

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

  Conciseness5/5

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

  The description is extremely concise, consisting of two short sentences with no unnecessary words. The critical scoping detail (path relative to FSGUARD_ROOT) is front-loaded in the second sentence, ensuring the agent reads it.

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

  Completeness4/5

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

  For a simple read operation with one parameter and no output schema, the description is largely sufficient: it states the tool's function and the key path constraint. Minor gaps (such as return format and error behavior) are not critical given the simplicity, but a bit more detail could improve completeness relative to an agent's expectations.

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

  Parameters4/5

  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. It does so by explaining the crucial semantic of the path parameter: relative to FSGUARD_ROOT. This adds significant meaning beyond the bare schema, though it does not cover other potential constraints like allowed file types or size limits.

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

  Purpose5/5

  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 'text file contents', making the tool's purpose unambiguous. It also specifies that the path is relative to FSGUARD_ROOT, which differentiates it from sibling tools like fs_write, fs_list, fs_search, and fs_move.

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

  Usage Guidelines3/5

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

  The description implies usage (reading file contents) but does not explicitly mention when to avoid this tool or provide alternatives. Unlike get_calls which names a sibling, here the sibling tool names are enough to infer differentiation, but no formal guidance is given. The intended context is clear from the verb 'read'.

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

• fs_writeA
  4/5.0
  Behavior4/5

  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 reveals that the operation overwrites existing content, creates parent directories as needed, and is restricted to FSGUARD_ROOT. This covers key side effects and constraints. It does not mention permissions, failure modes, or atomicity, but for a simple write operation the core behaviors are well disclosed.

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

  Conciseness5/5

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

  The description is two concise sentences with no unnecessary words. It front-loads the primary action and immediately follows with important behavioral details. Every word adds value, making it an exemplar of efficient writing.

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

  Completeness4/5

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

  For a simple two-parameter write tool, the description covers the essential behavior: creating/overwriting, parent directory creation, and the root restriction. It lacks details like return values or error handling, but those are not critical for an agent to invoke the tool correctly. Given the tool's simplicity, the description is sufficiently complete.

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

  Parameters3/5

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

  The input schema has 0% description coverage, so the description must compensate. It clarifies that 'content' is text and 'path' can include nested directories (since parents are created) and must be within FSGUARD_ROOT. However, it does not explicitly define the format of 'path' (relative vs absolute) or provide examples. It adds some semantic value but is not fully explanatory.

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

  Purpose5/5

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

  The description clearly states the action ('Write'), the resource ('a text file'), and the behavior ('creating or overwriting'). It also notes the automatic creation of parent directories, which distinguishes it from a simple write. The sibling tools (read, list, search, move) are clearly distinct, so purpose is unambiguous.

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

  Usage Guidelines3/5

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

  The description implies when to use this tool (for writing files), but does not explicitly state when not to use it or point to alternatives. There is no mention of exclusions or conditions, such as 'use fs_move to relocate files' or 'use fs_append for non-overwriting writes.' The intended usage is inferred from the verb and siblings, but not explicitly guided.

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

• git_stageA
  4/5.0
  Behavior5/5

  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 does this exceptionally well by revealing two critical behaviors: (1) every path is validated against FSGUARD_ROOT, and (2) a path escaping the root causes the entire call to fail, staging nothing. This goes far beyond what the schema provides and directly affects how an agent should reason about success/failure and safety.

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

  Conciseness5/5

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

  The description is a single, compact sentence that leads with the core purpose ('Stage files for commit') and immediately follows with the crucial safety behavior. There is zero filler, and the most important operational detail (path validation) is front-loaded. Every word earns its place.

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

  Completeness3/5

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

  For a tool with two parameters, no output schema, and no annotations, the description covers the purpose and a key safety behavior but omits essential operational details. It does not state what a successful staging returns, whether the repo_path must already be initialized (though sibling git_init_repo implies it may be), or how paths are interpreted (relative to repo_path?). While the safety note is valuable, the description leaves an agent guessing on parameter semantics and success indicators, so it is not fully complete.

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

  Parameters2/5

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

  The schema has 0% description coverage for its two parameters (repo_path and paths). The description does not explicitly explain these parameters beyond implying that 'paths' are files to stage and 'repo_path' is the repository location. It fails to clarify format (e.g., absolute vs relative paths), whether paths are relative to repo_path, or any constraints on repo_path. Given the low coverage, the description should have compensated with parameter details, but it does not.

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

  Purpose5/5

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

  The description clearly states the tool's purpose: 'Stage files for commit.' This is a specific verb ('stage') with a clear resource ('files for commit'), which distinguishes it from sibling Git tools like git_init_repo, git_repo_status, git_commit_repo, git_diff_repo, and git_log_repo. No ambiguity about what it does.

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

  Usage Guidelines3/5

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

  The description implies usage context: you stage files before committing. It does not explicitly mention when not to use it or alternative tools (e.g., 'use git_commit_repo to commit the staged files'), but the purpose is clear enough that an agent could infer its place in the workflow. It also highlights a critical constraint (path validation against FSGUARD_ROOT) that acts as guidance for safe usage, though it does not name alternatives.

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

• fs_moveA
  4.2/5.0
  Behavior4/5

  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 covers key behaviors: the FSGUARD_ROOT constraint, overwriting behavior for existing destination files, and failure on existing destination directories. These are critical edge cases. It doesn't mention permissions, reversibility, or what happens if the source doesn't exist, but the provided details adequately outline the operation's behavior for typical use.

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

  Conciseness5/5

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

  The description is two sentences long, front-loaded with the purpose, and includes all necessary behavioral constraints without redundancy. Every sentence adds value—there is no filler or repetition. This is exemplary conciseness for a tool definition.

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

  Completeness4/5

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

  Given the tool's complexity (move/rename with edge cases), the schema has no descriptions, no output schema, and no annotations, the description covers the essential aspects: the root constraint, overwrite behavior, and directory failure. It omits minor details like behavior when source is missing or return value expectations, but the absence of an output schema reduces the need to describe returns. Overall, it is adequately complete for an agent to call the tool correctly.

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

  Parameters3/5

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

  Schema coverage is 0% (no per-parameter descriptions), so the description must compensate. It adds meaning by explaining both parameters must resolve within FSGUARD_ROOT and describes destination behavior. However, it does not explicitly define source as the current path and destination as the target path, nor does it specify path format (absolute vs relative). The added semantics are helpful but not fully comprehensive for a 0% coverage case.

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

  Purpose5/5

  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 a specific verb+resource combination: 'Move or rename a file/directory.' This immediately distinguishes it from siblings like fs_read, fs_write, fs_list, and fs_search, which cover other file operations. No ambiguity remains about what the tool does.

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

  Usage Guidelines4/5

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

  The description provides clear context for when to use the tool (moving/renaming within FSGUARD_ROOT) and includes specific edge-case behaviors (overwrite on existing file, failure on existing directory). However, it does not explicitly mention alternatives or when not to use it, which would push it to a 5. The guidance is sufficient for an agent to decide this is the right operation among file tools.

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

• fs_searchA
  4.2/5.0
  Behavior4/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly discloses a critical behavior: 'Any match that resolves outside FSGUARD_ROOT — e.g. via a symlink — is silently excluded rather than reported.' This is non-obvious and crucial for an agent to know. It also mentions recursion. However, it does not describe the return format or error handling, which would be helpful but is not essential for a simple search tool.

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

  Conciseness5/5

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

  Two sentences, no filler. The first sentence front-loads the primary purpose with a concrete example; the second adds a relevant caveat about sandboxing. Every word earns its place, and the structure is efficient and scannable.

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

  Completeness4/5

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

  Given the simplicity (2 params, no output schema), the description covers the essential context: recursion, glob matching, and the sandbox exclusion. It could explicitly state what the tool returns (e.g., a list of file paths) but that is inferable from 'Find files'. The non-obvious symlink behavior is disclosed, which is the most important missing context. Overall adequate for an agent to call it correctly.

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

  Parameters4/5

  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. It explains the 'path' parameter as the base directory ('under path') and 'pattern' as a glob pattern with an example ('*.py'). This adds meaning to both parameters beyond the bare schema definitions. It could be more explicit about the path default and relative vs absolute paths, but the core semantics are clear.

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

  Purpose5/5

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

  The description clearly states the tool's function: 'Find files matching a glob pattern under path, recursively.' This specifies the verb (find), resource (files), and the pattern-matching behavior, distinguishing it from siblings like fs_list (which presumably lists without pattern filtering) and fs_read (which reads content). No ambiguity.

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

  Usage Guidelines3/5

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

  The description implies usage (searching for files by pattern) but does not explicitly state when to prefer it over alternatives like fs_list or when not to use it. It does not mention any exclusions or competing tools, leaving the choice to inference. A clear 'use this instead of fs_list when filtering by pattern' would elevate this.

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