MCP Canary

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new context: prices are in cents and the free trial requires no payment and begins on the first monitor write, which is behavior an agent could not infer from structured fields.

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 short sentences, zero filler, with the returned content stated first and the trial caveat second. Every sentence carries 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?

An output schema exists, so return values need not be spelled out; the description covers units and the trial trigger, which are not schema-level concerns. The only gap is the absence of any routing versus inspect_endpoint.

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 tool takes zero parameters, so the baseline is 4; there is nothing for the description to clarify beyond confirming this is a parameterless catalog lookup.

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 names the concrete content returned: plans, monthly prices in cents, limits, and the free trial. That is specific enough for an agent to know this is a pricing-catalog read, though no verb is stated and it does not explicitly distinguish itself from inspect_endpoint.

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?

Usage is only implied — an agent infers it should call this before subscribing or when it needs plan/limit data. There is no explicit when-to-use statement and the sibling inspect_endpoint is never mentioned as an alternative or complement.

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?

Beyond the annotations, the description discloses key behavior: it never calls a tool on the target, uses Streamable HTTP then legacy SSE, and reports target problems as status=failed with stable codes such as TARGET_UNAVAILABLE and TARGET_AUTH_FAILED. It also adds the security constraint that private and loopback addresses are rejected.

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 front-loaded with the core operation and remains compact. Every sentence adds operational value: transport behavior, no-tool-call guarantee, failure semantics, and address restrictions.

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 an output schema, rich annotations, and full parameter descriptions, the description supplies the remaining operational context an agent needs. It covers connection behavior, safety boundaries, failure reporting, and address restrictions without over-explaining return values.

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 url and headers parameters are already documented in the input schema. The description adds context about the target endpoint but does not add syntax or meaning beyond what the schema provides for either parameter.

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-and-resource operation: connects to a remote MCP endpoint, lists its tools, and classifies side effects. It also names the transport sequence and the no-tool-execution boundary, so an agent can distinguish this inspection tool from ordinary MCP calls.

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 gives clear context for when the tool applies: inspecting a remote MCP endpoint without invoking its tools. It also states an explicit exclusion—private and loopback addresses are rejected—but does not name alternatives or provide a fuller when-not-to-use policy.

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