mcp-shield

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

Without annotations, the description carries the full burden. It mentions what is returned (score, grade, findings, certification status) and implies a read-only operation, but does not explicitly state it is non-destructive or idempotent. Additional behavioral details like rate limits or authentication needs are absent.

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 informative sentence with no wasted words. The description is front-loaded with the core action 'Look up the trust score' and quickly specifies the resources and return values.

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 provides a reasonable overview of what the tool does and returns. It covers the two lookup methods and the key return fields, making it mostly complete for a simple lookup tool. Minor gaps like explanation of 'trust score' are acceptable.

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 both parameters described. The description adds value by clarifying that either a URL or npm package name can be used, which is not explicitly stated in the schema. This helps the agent understand mutual exclusivity, though not stating it as required.

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 'look up' and resource 'trust score', clearly identifying the tool's function. It distinguishes from sibling tools like scan_server or search_registry which perform different 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 clearly indicates the tool is for looking up trust scores by URL or npm package name, providing clear context. However, it does not explicitly state when not to use it or suggest alternative tools for different scenarios.

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 the description must cover behavior. It only states it retrieves statistics, without disclosing read-only nature, permissions, rate limits, or whether it's cached. Minimal disclosure beyond basic purpose.

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 efficiently states the purpose and provides examples. While it includes 'and more,' which adds vagueness, the structure is otherwise clear and 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?

With no parameters and no output schema, the description must fully explain the output. It lists some statistics but ends with 'and more,' leaving ambiguity. No details on format, units, or ordering are provided, making it incomplete.

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?

No parameters exist, and schema coverage is trivially 100%. The description adds value by listing the returned statistics (total indexed servers, live verified count, etc.), which helps the agent understand what to expect despite the lack of output 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 retrieves CraftedTrust ecosystem statistics, listing specific metrics. While it distinguishes from sibling tools implicitly (aggregate stats vs. individual checks or scans), explicit differentiation is missing.

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 siblings like check_trust or scan_server. The description lacks context about scenarios or prerequisites, leaving the agent without decision support.

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. It mentions return values (trust score, grade, security findings) but fails to disclose important traits such as whether the scan is destructive, whether it modifies state, expected duration, rate limits, or if results are cached. The verb 'Trigger' implies a side effect but lacks detail.

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 two short sentences, front-loading the action verb 'Trigger'. Every word serves a purpose; there is no redundancy or filler.

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 one-parameter tool with no output schema and no annotations, the description adequately states the action and return type. However, it could provide more context about scan duration, whether results are stored, and how it differs from siblings like check_trust. Given the presence of sibling tools, more distinction 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?

With 100% schema coverage, the schema already documents the single parameter (server_url) sufficiently. The description adds no additional meaning beyond what the schema provides, meeting the baseline expectation but not going beyond.

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 triggers a live trust scan of an HTTP/HTTPS MCP server and returns trust score, grade, and security findings. It uses a specific verb ('Trigger') and resource ('MCP server'), and distinguishes from siblings like check_trust (likely checking existing trust) and search_registry (searching).

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 (to perform a scan) but does not explicitly state when not to use or provide comparisons with siblings like check_trust or get_stats. There is no guidance on prerequisites or frequency limits, leaving the agent to infer 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 must fully disclose behavioral traits. It describes filtering but does not state whether the operation is read-only, safe, or if there are any destructive effects or rate limits. For a search tool, the implied behavior is non-destructive, but this is not explicitly confirmed, leaving uncertainty.

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 concise—two sentences that immediately state the purpose and key filter options. No redundant or wasted words. The structure is front-loaded with the primary action, making it easy for an agent to quickly understand the tool's function.

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 five parameters, no output schema, and no annotations, the description is too sparse. It does not explain the search algorithm (exact match, fuzzy?), the result format, pagination behavior (though limit is a parameter), or default filtering when no parameters are provided. An agent would need more context to use the tool 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 input schema has 100% coverage, so each parameter is already documented. The description adds a paraphrased summary ('Filter by grade, certification, or scan type') but does not provide additional meaning or usage details beyond the schema. 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 tool's purpose: searching the CraftedTrust registry overlay for MCP packages and servers. It uses a specific verb-resource combination ('Search ... registry overlay') and lists filterable attributes (grade, certification, scan type). This distinguishes it from sibling tools like check_trust, get_stats, and scan_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: when you need to search and filter the registry. However, it does not explicitly state when to use this tool versus alternatives (e.g., check_trust for trust checks), nor does it mention any prerequisites or exclusions. The guidance is adequate but not explicit.

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