SBGrid3.0 MCP

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

With no annotations, the description carries full burden but only says 'Get detailed documentation'. It does not disclose output format, authentication needs, or any side effects. The included warning about code generation guidelines is unrelated to 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 first sentence is concise, but the second sentence is a long, unrelated warning about SBGrid3 code generation guidelines that adds clutter and may confuse the agent. Not every sentence earns its place.

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

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

For a simple documentation retrieval tool with one parameter and no output schema, the description is minimally complete. However, it lacks details on what the documentation contains (e.g., endpoints, parameters) and includes extraneous information, reducing completeness.

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

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

The parameter 'name' has schema coverage of 100% with description 'Exact API name'. The tool description repeats this but adds no additional semantics. Baseline 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 verb 'Get', the resource 'detailed documentation for a specific SBGrid3 API', and the condition 'by exact name'. It distinguishes from sibling tools: listSBGridAPIs lists all, searchSBGridAPI searches, getSBGridExample gets examples.

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

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

The description implies usage when the exact API name is known, but does not explicitly provide when-to-use or when-not-to-use guidance compared to siblings. No alternatives or exclusions are mentioned.

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

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

With no annotations, the description carries full burden but only states it 'searches' without clarifying behavior like read-only nature, required permissions, rate limits, or what constitutes a 'code example' (e.g., returns snippets or references). The warning hints at generation context but not tool operation.

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

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

The description is short but mixes English purpose with a Korean warning about server instructions, which is not concise. The warning distracts from the tool's primary function and would be better placed elsewhere. The structure could be improved by keeping the purpose separate.

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 search tool with two parameters and no output schema, the description lacks completeness: it does not describe what results look like, how many examples are returned, or how the query is matched. The sibling tools are present but no distinguishing context is provided.

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

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

Schema description coverage is 50% (only 'query' has description). The description adds minimal value by rephrasing 'query' as 'feature or use case', but offers no explanation for 'limit'. With partial coverage, the description should compensate but does not.

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

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

The description clearly states the tool searches for SBGrid3 code examples by feature or use case, distinguishing it from sibling tools that focus on API details, listing, or searching APIs. However, the inclusion of a Korean warning about generation guidelines slightly dilutes the primary purpose statement.

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

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

No guidance on when to use this tool vs. siblings like searchSBGridAPI or listSBGridAPIs. The Korean text provides context for code generation but does not help the agent decide between tools. Missing explicit 'when-not-to-use' or alternative recommendations.

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 provided, so description carries full burden. Only a warning about SBGrid3 code generation, but no disclosure of behavioral traits like default behavior or output format.

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

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

Two sentences, but the second is a warning in Korean that may not be directly relevant to the tool's operation. Somewhat concise but could be clearer.

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?

No output schema, and description lacks information about return value, default behavior when no category provided, or example usage. Incomplete for a simple listing tool.

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

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

Schema coverage is 0%. Description mentions 'category' but does not explain possible values, format, or default. Does not compensate for lack of schema documentation.

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

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

Clearly states 'List all SBGrid3 APIs in a specific category,' using a specific verb and resource. Distinguishes from siblings like getSBGridAPIDetail and searchSBGridAPI.

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

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

No guidance on when to use this tool versus alternatives. Does not mention when to use list vs search or get detail.

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

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

With no annotations provided, the description carries full responsibility but fails to disclose behavioral traits such as whether results are returned, pagination, or read-only nature. The ⚠️ warning is about unrelated instructions, not 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 English sentence is concise, but the appended Korean block is irrelevant to the tool's functionality and consumes space without adding value. Removing the Korean text would improve 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 no output schema and simple input, the description should explain return value or behavior. It does not mention what the search returns, how results are structured, or any limitations. The Korean text is out of context.

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

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

The description adds no meaning beyond the schema: 'query' is already described as 'Search keyword' and 'limit' is entirely undocumented in both places. Schema coverage is 50% and description compensates nothing.

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

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

The description explicitly states 'Search SBGrid3 API documentation by keyword,' clearly indicating verb and resource. It distinguishes from siblings that list, detail, or get examples. However, the inclusion of unrelated Korean instructions detracts from clarity, preventing 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?

No guidance on when to use this tool versus alternatives like listSBGridAPIs or getSBGridAPIDetail. The additional Korean text discusses code generation conventions, not tool usage, leaving usage entirely implicit.

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