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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered. The description adds the scoping constraint that it reads the project's recent commit history, which aligns with the annotations but does not disclose additional behavioral details such as sorting, output format, or side effects. Since the description does not contradict annotations and adds only scoping context, a 3 is appropriate.

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

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

The description is a single concise sentence that states the tool's purpose without wasted words. The key information (viewing recent commit history) is front-loaded, and there is no extraneous repetition of schema or annotation content.

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

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

For a simple tool with one optional, well-documented parameter, a read-only annotation profile, and an output schema, the description covers the essential purpose and scope. It does not include when-to-use guidance, which would enhance completeness, but the low complexity and rich schema make the missing guidance a minor gap rather than a critical one.

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 the count parameter fully described as '要看最近幾筆 commit'. The tool description doesn't add information about parameters beyond what the schema provides, so the baseline of 3 applies.

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

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

The description uses a specific verb ('查看' / view) and a specific resource ('專案最近的 git commit 紀錄' / recent git commit history of the project). It clearly distinguishes git_log from sibling tools like list_files, run_tests, and read_file, which handle different concerns. An agent can tell this is the tool for commit history at a glance.

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 explicit guidance on when to use this tool versus alternatives. There is no mention of 'use when you need to inspect commit history' or any exclusion/alternative statements. The context signals only list sibling tool names, but the description itself does not state any selection criteria.

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

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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no additional behavioral context such as recursion behavior, sorting, or hidden files, but it also does not contradict the annotations.

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

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

The description is a single, concise sentence that immediately communicates the tool's purpose. Every word contributes value, and the glob-style detail is front-loaded.

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

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

For a simple read-only listing tool with full schema coverage and an output schema, the description is adequate for an agent to select and invoke the tool. It could mention scope nuances like whether subdirectories are included by default, but the default glob pattern already implies recursive behavior.

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

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

Schema description coverage is 100%, so the parameters are already fully documented in the schema. The description only restates the glob concept already present in the schema, adding no extra semantic meaning beyond what the structured input already provides.

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

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

The description clearly states a specific verb and resource: listing files in the project using a glob pattern. It is distinct enough from siblings like read_file or run_tests, though it does not explicitly differentiate itself from alternatives.

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

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

The description implies the tool is for enumerating project files via glob patterns, but it offers no explicit guidance on when to choose it over siblings or when not to use it. There are no exclusion criteria or alternative tool references.

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

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

Annotations already cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds one useful behavioral detail: content is returned with line numbers, which clarifies the output format. It doesn't mention edge cases, but the read-only nature is already disclosed by annotations.

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

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

The description is a single, well-formed sentence that immediately states the action and expected result. It front-loads the core purpose and includes the line-number caveat with no fluff or redundant phrasing.

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

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

For a simple read-only tool, the description, annotations, and full schema coverage collectively provide almost all necessary context. The output format is at least partially described (line numbers), and the schema covers parameters and constraints. A minor gap is the lack of any note on error behavior, but with annotations and output schema present, this does not undermine correct invocation.

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

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

Schema description coverage is 100%; both path and max_lines already have rich documentation in the input schema (relative path example, limits, default). The description adds nothing about parameters beyond what the schema provides, so the baseline 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 states a specific verb ('讀取' / 'read'), a specific resource ('專案內的一個檔案' / 'a file in the project'), and the output ('回傳內容（附行號）' / returns content with line numbers). This makes the tool's purpose unmistakable and clearly distinguishes it from sibling tools like list_files, run_tests, and git_log.

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 simply states what it does, with no mention of when to prefer read_file over list_files, run_tests, or git_log, nor any exclusions or conditions.

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

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

The annotations are all false, giving no indication of side effects. The description does not mention any potential effects (e.g., creating cache files, modifying the environment). No extra behavioral detail is provided.

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

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

The description is a single, concise sentence that conveys the purpose 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?

The tool is simple with one parameter and a clear purpose. The description mentions 'in the project' providing context. An output schema exists, so return values are not required to be described. Minor gap: no explicit statement about the working directory, but it is implied.

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 parameter 'target' has a description in the schema, so the schema coverage is high. The tool description itself adds no additional parameter semantics beyond what the schema already provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the action (run pytest) and the result (return a summary). It distinguishes the tool from sibling tools like list_files or git_log.

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

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

The description implies when to use the tool (when tests need to be run) but does not provide explicit guidance on alternatives or when not to use it. The parameter description gives some context but no comparative guidance.

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