MCP Queen

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

With no annotations, the description carries the full burden. It clearly indicates a read-only operation ('Get') and specifies the output contents (grade and probe evidence). No hidden side effects or prerequisites are mentioned, which is acceptable for a simple retrieval 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?

A single sentence that is front-loaded with the core purpose and includes a specific example. Every word is informative and there is no superfluous text.

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

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

Given the absence of an output schema, the description could be more explicit about the structure of the response (e.g., whether evidence is an array, what a grade looks like). The current description is adequate but leaves room for ambiguity about the exact return format.

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

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

The schema already describes the parameter 'name' as 'Registry server name'. The description adds valuable context by providing a concrete example format (e.g., 'com.healthai/radar'), clarifying the expected input convention beyond the schema.

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

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

The description clearly states the verb 'get' and the resource 'full grade and verbatim probe evidence' for a single MCP server. It specifies the unique identifier format 'official registry name (e.g. com.healthai/radar)', which distinguishes it from sibling tools like list_grades or search_servers.

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 using this tool when you need detailed grade data for a specific server and have its exact registry name. However, it does not explicitly state when not to use it or provide alternatives like search_servers for name discovery.

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 the full burden. It clearly states the output fields (grade, score, latency, tool count, auth state) and mentions 'deterministic probe grades with evidence,' indicating reliability. However, it does not explicitly state that it is read-only or disclose ordering/pagination 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 two sentences with no unnecessary words. The first sentence states the purpose and nature, the second describes the return fields. Every sentence adds value.

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

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

Given the tool has only one optional parameter and no output schema, the description provides a good overview of return fields. It is mostly complete, though a note about sorting order (e.g., by score descending) would enhance 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 the 'limit' parameter with default and max. The description does not add any additional parameter information, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action ('list') and the resource ('top graded MCP servers from the mcpqueen registry'). It also distinguishes from siblings by mentioning 'deterministic probe grades with evidence' and implying a list of top servers, whereas siblings like get_server_grade focus on a single server.

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

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

The description implies usage for viewing top-graded servers but does not explicitly state when to use this tool over alternatives like get_server_grade or search_servers. No when-not or alternative guidance is provided.

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. It discloses that results are 'best-graded matches' and include URLs, but does not mention any behavioral traits like rate limits, authentication, or side effects.

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

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

Two sentences, no wasted words. First sentence states purpose with examples, second adds return value and filter. Front-loaded and efficient.

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

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

For a tool with 3 parameters and no output schema, the description covers what it does, what it returns (best-graded matches with URLs), and optional filter. Could mention default limit or behavior if no results, but schema covers limit details.

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?

All parameters (query, limit, category) are described in the schema. The description adds context by explaining search semantics (keyword/task), result ranking, and optional filtering, enhancing understanding beyond schema.

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

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

The description clearly states the tool searches the MCP registry for servers matching a task or keyword, returns best-graded matches with URLs, and supports optional category filtering. This distinguishes it from sibling tools like get_server_grade, list_grades, and submit_feedback.

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?

Provides example queries ('postgres', 'send email') and mentions optional category filter, guiding when to use. However, lacks explicit when-not-to-use or comparison with siblings for 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?

No annotations are provided, so the description carries the full burden. It discloses that the search is live from tools/list and returns server, grade, and endpoint. However, it does not mention pagination, rate limits, or side effects. For a read-only search tool, the behavioral disclosure is adequate but not exhaustive.

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 with no redundancy. The first sentence defines the action and scope; the second provides usage guidance. Every word contributes value.

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

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

Given the tool's complexity (3 params, no output schema), the description covers the core purpose and usage context. It mentions the return fields (server, grade, endpoint) and the search domain. It does not detail the return format but is sufficient for selection.

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 100%, so the description adds marginal value beyond the schema. It clarifies that 'query' matches against tool names and descriptions, but does not elaborate on 'limit' or 'category' beyond what is in the schema.

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

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

The description clearly states the tool searches across actual MCP tool definitions (names and descriptions) from graded servers, distinguishing it from server metadata search. The verb 'search' and resource 'tools' are explicit.

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 usage context: 'Use this when you need a specific capability or data type' with concrete examples. It does not explicitly exclude alternatives but contrasts with server search via 'not just server metadata'.

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, description carries full burden. It discloses key behavioral traits: reports are quarantined for human review and never auto-published. Does not discuss return value or acknowledgment, but sufficient for a submission 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?

Two sentences, front-loaded with purpose, no redundant information. Every sentence adds value.

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 no annotations, but description adequately explains submission behavior, constraints (quarantine, content types), and the subject. Minor gap: no mention of return value, but acceptable for a simple submission.

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 100% with each parameter having a description. The tool description adds no additional param-specific meaning beyond what schema provides, so 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 tool submits a field report about a used MCP server, specifying content (what worked, failed, surprising behavior) and distinguishes from siblings which are informational (get_server_grade, list_grades, search_servers).

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?

Clear context for when to use: when providing feedback on actual MCP server usage. No explicit when-not-to-use or alternatives, but siblings serve different purposes, making usage intuitive.

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