VoiceCheap

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the safety profile is fully covered. The description adds genuine value by enumerating the response contents (identity, effective plan, included vs. purchased minutes, TTS balance, connection permissions), which matters because there is no output schema. It does not mention whether balances are cached or when they refresh, a minor gap.

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 with no filler, front-loading the identity/plan information before the balance details. Given the absence of an output schema, every enumerated field earns its place.

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 zero-parameter, read-only tool with no output schema, the description supplies exactly the missing piece: what the response contains. Combined with annotations that fully cover the safety and idempotency profile, an agent has everything needed to call this 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The enumerated return fields are the closest analogue to parameter meaning and are stated clearly.

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 verb ('Get') plus a concrete resource set: account identity, plan, minute balances, TTS character balance, and connection permissions. An agent can tell instantly what comes back. It does not explicitly differentiate itself from the sibling action_request_get, but the enumerated resource makes the distinction self-evident.

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?

There is no explicit when-to-use or when-not-to-use statement, and the sibling action_request_get is never referenced. Usage is nonetheless strongly implied: a zero-parameter read of 'your account' is unambiguously the first call an agent makes to learn its identity, plan, and remaining quota, so inference is low-risk.

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 declare readOnly, idempotent, non-destructive behavior, so the description earns credit for going beyond them: it discloses the authorization requirement ('Requires every permission of the original action') and adds a prompt-injection guardrail about results and media being data. It does not describe polling cadence, terminal states, or what an in-progress response looks like.

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?

Three short, front-loaded sentences with the core action first, then the authorization constraint, then the safety note. The final sentence is close to boilerplate but is short and does carry a real guardrail, so it roughly earns its place.

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 two-parameter, idempotent read-only polling tool with no output schema, the description covers the inputs, the auth requirement, and the nature of the payload. It omits how to interpret completion status, which an agent polling an async action would find genuinely useful, keeping it below 5.

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 0%, so the description must carry parameter meaning. It names both parameters semantically ('operation name and requestId'), which is better than nothing, but adds no format, casing, or UUID-shape guidance beyond what the schema's pattern/format fields already enforce structurally.

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 (poll) and resource (asynchronous/previously submitted action) with the two identifiers needed to find it. The sibling tool account_get is unrelated, so differentiation is trivially clear; an agent knows exactly what this returns status for.

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 phrase 'poll an asynchronous or previously submitted action' establishes the usage context: an agent calls this when it has already kicked off an async action and holds an operation/requestId pair. It gives no explicit exclusions or alternative paths (e.g., what to do if the action has not been submitted), so it stops short of 5.

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