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

With no annotations, the description carries full burden: it does disclose the read-only nature ('without creating a recording') and the exactly-one-ID constraint, which is useful. But it omits auth requirements, what happens if the ID is unknown, and whether the returned job may still be in progress, which matters for a job-status tool.

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, front-loaded with the action and the key constraint, with zero waste.

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 simple 2-param read tool this is close, but with no annotations, no output schema, and no parameter descriptions, the description should say more about what a job read returns (status fields?) and error behavior for unknown IDs.

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 0%, so the description must compensate, and it does: it explains that job_id is the job UUID, request_id is the caller-known request UUID, and that exactly one must be supplied (matching the oneOf). It adds genuine semantics the schema lacks, though it doesn't clarify format or how to obtain each ID.

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 ('Read') and resource ('an existing job'), and names both lookup keys. It also implicitly distinguishes itself from the sibling TTS tools by saying 'without creating a recording', though it doesn't name those siblings explicitly.

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 'without creating a recording' implies this is the non-mutating lookup path, which hints at when to use it versus flowspeech_tts. However, there is no explicit when/when-not guidance, no mention of flowspeech_new_request_id as the source of request_id, and no stated alternative.

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 the full burden. 'Retrieve' implies a read operation, but there is no mention of permissions, rate limits, whether results are cached, or whether the catalog is paginated — all of which matter for a listing tool.

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?

One short sentence with no wasted words and the verb-resource pair front-loaded. It is efficient but borders on under-specified rather than deliberately terse.

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 output schema and no annotations, the description should say what the catalog contains (voice IDs, names, languages, genders) so an agent knows what it can extract. That information is absent, leaving the agent unable to plan the follow-up call to flowspeech_tts.

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% and the single optional 'gender' parameter (enum male/female/all with default 'all') is never acknowledged in the description. The schema's enum values are self-explanatory, but the description adds nothing about what filtering means or how 'all' behaves.

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?

Specific verb (Retrieve) plus specific resource (voice catalog) from a named service. The resource is clearly distinct from sibling tools like flowspeech_tts, flowspeech_quota, and flowspeech_get_job, though the description never explicitly contrasts with them.

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 call this versus alternatives, nor any note that it is the discovery step for voice IDs consumed by flowspeech_tts / flowspeech_tts_multi. The reader must infer that from sibling names alone.

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?

With no annotations present, the description does real work: it discloses that generation is local, requires no network, and needs no API key — covering the auth and side-effect questions an agent would otherwise have to guess at. It stops short of saying whether the UUID is persisted or how it relates to server-side records.

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, front-loaded with the operation and its constraints. The second sentence is worth including but its phrasing is loose enough to require a re-read.

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 utility with no output schema, the description covers purpose, execution environment, and timing well enough to call it correctly; the return value (a UUID string) is only implied by the word 'UUID' but is inferable.

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; baseline 4 applies. The description correctly implies no configuration is needed.

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 and resource ('Generate a fresh request UUID') plus the key execution constraint ('locally, without network access or an API key'). No sibling tool (tts, tts_multi, list_voices, quota, get_job) overlaps with this operation, so an agent can identify it unambiguously.

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 second sentence ('Keep it before starting one recording') implies a call-ordering rule but is awkwardly phrased and never names which sibling operation starts a recording, nor what happens if an ID is reused. Usage is implied rather than specified.

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 carry the behavioral load. "Read" correctly signals a non-mutating operation, but it says nothing about whether this call itself consumes credits, whether it requires authentication, or whether the numbers are cached/realtime — all relevant for a billing-adjacent endpoint. Adequate for a trivial zero-arg read, but not rich.

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?

One sentence, nine words, front-loaded with the verb and enumerating exactly the three values returned. No filler, no restatement of the tool name.

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, no-output-schema tool this is close to sufficient — the description names the three returned quantities so the agent knows what to expect. Slightly short of 5 because units/format of the returned credits and any auth or rate-limit expectations are left unstated.

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, which is the baseline-4 case. The description correctly implies a global account-scoped read with no filtering knobs, consistent with the empty 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?

Specific verb ("Read") plus a precise resource ("available, remaining and reserved API credits"), including the three credit buckets returned. Nothing in the sibling list (tts, tts_multi, list_voices, get_job, new_request_id) overlaps with a credit-balance read, so an agent can route here unambiguously.

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 usage is implied by the noun "quota" — an agent would call this to check balance before or after synthesis requests — but the description never says when to call it (pre-flight check? error diagnosis? periodic polling?) or that no alternatives exist. No exclusions or triggering conditions are stated.

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?

With no annotations, the description carries the full burden and does well by disclosing auth needs, paid access, credit consumption, and WAV output. It still omits operational behavior such as whether generation is synchronous or job-based and how failures are surfaced.

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 tight sentences with the main action and requirements front-loaded. Every clause earns its place by communicating purpose, prerequisites, or cost.

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 covers the core purpose, prerequisites, and cost, which is useful. But with no output schema, it does not explain what is returned—file path, job identifier, or otherwise—and the presence of flowspeech_get_job suggests result handling may matter.

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 50%, and the description mainly restates that a caller-known request UUID is required. It does not add meaning for text, voice, or output_path beyond what the schema already provides, so it only partially compensates for the coverage gap.

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 output resource: generate a WAV recording with FlowSpeech. It is clear what the tool does, but it does not distinguish this single-recording tool from the sibling flowspeech_tts_multi.

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 prerequisites—caller-known request UUID, API key, paid API access, and credit consumption—which helps determine whether the tool is usable. However, it does not say when to choose this over flowspeech_tts_multi or how to obtain the UUID without relying on the schema.

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?

With no annotations, the description carries the full behavioral burden. It usefully discloses that it consumes account credits and produces a WAV recording, but it does not cover permissions, failure behavior, idempotency, or what the caller receives back.

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 three short sentences, front-loaded with the core action and output format. Every sentence adds useful information: the output type, the turn-prefix format, and the credit consumption.

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 five-parameter tool with no annotations and no output schema, the description is only partially complete. It covers the output artifact and text-turn format, but omits the speaker-to-voice mapping, where the resulting WAV is written, and what the tool returns to the caller.

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 40%, so the description must compensate. It adds critical meaning for the text parameter by explaining that each turn begins with Speaker1: or Speaker2:, but it does not explain how voice_a and voice_b map to those speaker labels, nor does it clarify text formatting beyond the prefix rule.

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: 'Generate a two-speaker WAV recording.' The 'two-speaker' qualifier implicitly distinguishes it from the single-speaker sibling flowspeech_tts, though that sibling is not named explicitly.

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 implied by 'two-speaker' and the need for a caller-known request UUID, which suggests when this tool is appropriate. However, it never explicitly says when to use this instead of flowspeech_tts or what prerequisites are required beyond getting a UUID.

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