Clean Table

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

Despite having useful annotations (readOnlyHint, idempotentHint), the description adds substantial behavior beyond them: deterministic behavior, a never-guess policy, exception-with-reason returns, per-cell re-checking, and the exact payment flow including the PaymentRequired response when unpaid. It enriches the annotations without contradicting them.

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?

Core behavior is front-loaded in the first sentence, followed by short, high-signal statements about exceptions, verification, determinism, and payment. No sentence is filler; even the payment sentence adds the x402/PaymentRequired flow rather than merely repeating the title's price.

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?

The description is comprehensive for a tool with no output schema: it explains outcome categories, exception semantics, idempotence, and payment prerequisites. The main gap is that the exact response envelope is implied ('exceptions are returned', 'delivered cells') rather than explicitly enumerated, but the agent has enough to invoke and handle the result correctly.

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 already 100%, so the baseline is 3; the description earns more by adding meaning absent from the schema: dates become ISO, money becomes numbers, text collapses, and deduplication is optional. The transformation semantics are explicitly stated beyond the raw property definitions.

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 opens with a specific verb and resource — 'Normalise a delimited table' — and enumerates concrete transformations: dates to ISO, money to numbers, text collapsed, optional deduplication. It is unmistakably distinct from the only sibling (mm_status) and adds paid service context rather than restating the tool name.

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 context for use is clear: use it when a delimited table needs normalization against a stated schema, with exceptions surfaced rather than guessed. It does not explicitly name an alternative condition or a when-not-to-use, but the sibling set is minimal and no confusing alternative exists, so this is strong but not exhaustive.

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?

Annotations already mark the tool as read-only, and the description adds meaningful context: it is a free health/status endpoint, includes a defined set of information, and explicitly states 'No secrets.' This goes beyond the annotation without contradicting it, though it does not detail response format or potential limitations.

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 short sentences with no filler. The core purpose is front-loaded, and every phrase adds value, including the security reassurance 'No secrets.'

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 parameterless, read-only status tool, the description is complete: it states what the tool returns, covers the free/paid dimension, and notes the absence of secrets. No output schema exists, but the enumerated content gives an agent enough to decide whether to call it.

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 has zero parameters, so the input schema is trivially complete. Per the baseline for parameterless tools, the description need not add parameter-level detail, and it appropriately focuses on the output instead.

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 a specific resource ('service status') and enumerates its fields (version, environment, network, autonomy mode, paid offer), making its purpose immediately clear. The scope is distinct from the sibling clean_table, so an agent can tell them apart without further investigation.

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 tool is for health/status checks, but it does not explicitly state when to use it versus alternatives or provide exclusion criteria. The sibling clean_table is unrelated, so there is no direct comparison, leaving usage context mostly implicit.

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