McpStamp Check

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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds genuinely useful behavior the annotations cannot express: a 10-minute result cache and how to bypass it with fresh=true. It omits any note about network/auth requirements or failure modes, which keeps it below a 5.

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?

Front-loaded with the core action, then return values, then the cache caveat. The long enumeration of return artifacts (score, grade, per-store readiness, failing checks, report URL, badge markdown) is slightly list-like, but every element is informative and nothing is 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?

With a full output schema, rich annotations and 100% param coverage, the description only needs to supply what structured fields cannot: the cache window and the fresh bypass, which it does. Nothing an agent needs to invoke this correctly is missing.

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 both parameters are documented structurally (baseline 3). The description reinforces the caching semantics of fresh ('set fresh to true to force a new check'), adding meaning beyond the raw field definition, though it does not elaborate on the URL format beyond what the schema shows.

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?

States a specific verb (Check) and precise resource (a public remote MCP server URL over Streamable HTTP), plus the exact standard it evaluates against (Claude Directory, ChatGPT Apps, Gemini Connected Apps, MCP Registry). It is clearly a readiness-audit tool, distinct from the sibling explain_check.

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 usage context (validating an MCP endpoint before listing in app directories) but never states when to prefer it over the sibling explain_check or what preconditions a candidate server must meet. The caching/fresh note is the only conditional guidance, and it is operational rather than about tool selection.

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 read-only, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds what the explanation contains and its relationship to check_mcp_server, but it does not disclose additional behavioral details such as invalid-id handling or error 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 tight sentences, front-loads the purpose, then adds scope and usage guidance without filler. Every clause contributes useful information.

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 full schema coverage, an output schema, and rich annotations, the description provides enough context for correct invocation. It states what the tool explains and when to reach for it after check_mcp_server, with no material omissions for a simple one-parameter read-only 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 description coverage is 100%, and the single parameter is a fully enumerated check_id with its own description. The description gives examples like tool_annotations and auth_prm and notes the id comes from a check result, but this largely repeats information already present 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 uses a specific verb and resource: 'Explain one McpStamp Check rule by its id.' It also enumerates what the explanation covers (what it tests, why stores need it, blocked stores, weight, source documents), making the tool distinguishable from the sibling check_mcp_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?

It explicitly says to use this tool after check_mcp_server to understand a failing check, giving clear context for invocation. It does not state when not to use it or name other alternatives beyond the sibling relationship.

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