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

The description adds substantial behavioral detail beyond the sparse annotations, including what status reports, the effect of each action, and the Windows limitation for pause/resume. It also discloses that clear stops playback and empties the queue, which is important side-effect information for an agent.

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 compact sentences deliver the purpose upfront and then map each action to its effect without wasted words. The structure is easy to parse and every phrase contributes meaningful 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?

For a tool with one enum parameter and no output schema, the description covers all actions, the scope of the queue, what status includes, and a platform caveat. Nothing essential for correct invocation 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?

The single parameter 'action' is an enum with 0% schema description coverage, so the description carries the full semantic burden. It explains each enum value—status, pause, resume, skip, clear—with specific behavioral meaning, which is exactly what the agent needs to choose correctly.

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: 'Inspect and control the shared audio queue,' which clearly distinguishes the tool from siblings like play_audio, speak, and queue_speech. It then enumerates each action and its concrete effect, leaving no ambiguity about what the tool does.

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 establishes a clear context for use: manipulating the shared audio queue, including status inspection, pausing, resuming, skipping, and clearing. It includes a platform exclusion for pause/resume on Windows, but does not explicitly name sibling tools or state when to prefer this over starting playback or queueing speech.

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 readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds a meaningful behavioral fact beyond annotations: the operation is 'Free,' meaning it does not consume credits, which is highly relevant for an account/credits 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?

The description is a single clear sentence that front-loads the action and resource, then lists the key returned fields. The additional 'Free.' note is short, purposeful, and earns its place by conveying cost behavior.

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 an empty input schema and no output schema, the description provides sufficient information: the resource, the main fields returned, and the cost implication. Nothing critical is missing for an agent to invoke it 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 input schema has zero parameters, and schema description coverage is 100%, so there is no parameter documentation burden for the description to carry. The description appropriately focuses on what the tool returns rather than parameters.

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 ('Show') and a clear resource ('the API key's account'), and lists the concrete outputs: credit balance, plan, and rate limits. This fully differentiates it from the unrelated sibling tools, which are all about speech, translation, OCR, or model listing.

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 makes it clear this is the tool for retrieving account-level information such as credits, plan, and rate limits. There are no account-related sibling tools, so no exclusion or alternative routing is needed; the context is sufficiently clear for an agent to select it.

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 readOnlyHint, idempotentHint, and destructiveHint, so the description is not burdened with restating those. It adds useful behavioral context by noting the tool is free and that results include limits and credit pricing, which helps the agent set expectations beyond the raw schema.

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 extremely concise, using one sentence plus a short standalone 'Free.' statement. It front-loads the core purpose and includes only necessary information, with no filler or repetition.

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, zero-parameter, read-only listing tool, the description is complete enough. It names the resource, indicates what kind of data is returned (limits and credit pricing), and states cost behavior. No output schema exists, but the description sufficiently orients an agent.

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, and the schema is empty with 100% coverage, so the baseline of 4 applies. The description adds no parameter detail because none is needed; it instead clarifies the content of the returned model listing.

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 clearly states the specific verb 'List' and the resource 'Paxa models', and adds valuable detail about what is included ('limits and credit pricing'). It is readily distinguishable from sibling tools like list_voices because it explicitly names models as the subject.

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 guidance on when to use this tool versus alternatives, nor any mention of what it is not for. The description implies a simple informational listing, but provides no exclusions or decision criteria relative to sibling tools.

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 readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is established. The description adds behavioral value by specifying the contents of the roster and adding 'Free,' which signals cost/auth expectations beyond the annotations.

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 a single sentence with no wasted words, front-loading the verb and resource before listing the output fields. The extra 'Free' marker is short and adds meaningful context.

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 list operation with no output schema, the description adequately covers what the agent will receive. It lacks explicit notes on pagination or sorting, but those are not essential for a simple voice roster and would be unexpected at this complexity level.

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 and 100% schema description coverage, so there are no parameter semantics for the description to clarify. A baseline of 4 is appropriate because nothing is missing or ambiguous.

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 ('List') and a clearly identified resource ('Paxa TTS voice roster'), then enumerates the returned fields: ids, names, gender, language, and character notes. This distinguishes it from sibling tools like list_models, speak, or get_account.

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 makes the use case clear: an agent needing voice metadata for Paxa TTS should call this tool. It does not explicitly name alternatives or exclusions, but the resource-specific wording leaves little ambiguity about when it applies.

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 indicate read-only, idempotent, non-destructive behavior. The description adds substantial extra context: supported file types, hard limits (50 pages, 10 MiB), cost per page, and the two return modes. This goes well beyond what annotations or schema alone convey.

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 concise sentences with no filler. The core operation and return format are front-loaded, followed by practical limits and cost. Every sentence adds 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?

For a simple two-parameter tool with safety covered by annotations, the description is complete: it specifies input path, supported formats, size/page limits, output format, and cost. No critical information for selecting or invoking the tool 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 already documented, providing a baseline of 3. The description adds meaningful constraints on file_path (local file, format limits, size/page limits) and clarifies output as Markdown or structured blocks, which is useful context beyond 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 clearly states a specific verb ('Run Paxa OCR') and resource (local PDF, PNG, JPEG, or WebP files) and specifies what is returned (content as GitHub-flavored Markdown or structured blocks). It is unambiguous and readily distinguished from the unrelated sibling tools.

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 gives clear conditions for use: local files of specific formats, up to 50 pages and 10 MiB, and notes the output modes. It does not explicitly name alternative tools or when-not-to-use cases, but no OCR alternative appears among the siblings, so the lack of an explicit exclusion is a minor gap.

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 description adds meaningful behavioral context beyond the annotations: 'Blocks until playback finishes' and 'Free (no API call)'. Since the annotations are all false and provide little behavioral signal, the description carries the transparency burden and does so adequately for a simple playback 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?

Three short sentences, each earning its place: what it plays, how it behaves (blocking), and its cost profile. The most important purpose is front-loaded. There is no redundant or filler content.

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 single-parameter tool with no output schema and minimal annotations, this description covers the essential facts: local file input, speaker output, blocking behavior, and cost. An agent has enough context to select and invoke the tool correctly without missing critical information.

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 only parameter, file_path, is already fully documented with supported formats. The tool description adds only 'local' and 'through speakers', which is already implied by the schema, so it provides no significant additional parameter meaning.

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 + resource ('Play a local audio file') and clarifies the output destination ('through this machine's speakers'). It also distinguishes itself from sibling generation tools by referencing files produced earlier by text_to_speech, so an agent can tell this is playback rather than speech synthesis.

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 gives clear usage context: use this when you have a local audio file (e.g. one produced by text_to_speech) and want to hear it through the speakers. It also implies cost guidance with 'Free (no API call)', though it does not explicitly contrast with alternatives like speak or queue_speech.

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 description discloses key behaviors beyond the annotations: it splits text into segments, synthesizes ahead while playing, returns immediately, preserves queue order, and costs 15 credits per 1000 characters. This is substantial behavioral context that annotations alone do not provide. No contradiction with readOnlyHint=false or idempotentHint=false.

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 dense, purposeful sentences. The main action is front-loaded, followed by the queuing behavior, control path, and cost. No filler or redundant restatement of the schema.

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 tool with no output schema, the description covers the key runtime behavior, return timing, queue ordering, cost, and monitoring mechanism. An agent has enough information to select, invoke, and manage this tool 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 100%, so the baseline is 3. The description adds extra meaning by relating the text parameter to cost per 1000 characters and by explaining how the text is processed into segments. This goes slightly beyond merely restating 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 opens with a specific verb and resource: 'Read long content aloud (stories, articles, books).' It clearly identifies the long-form, queued reading behavior and sets it apart from simpler or shorter utterances. The segmentation and ordering details make the tool's role unambiguous.

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 gives clear context: use it for long content, and it queues after existing audio. It also routes follow-up control to control_playback. However, it does not explicitly name when to prefer a sibling like speak or text_to_speech, so it stops short of full when/when-not guidance.

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 runtime behaviors: it blocks until playback finishes, waits for currently playing audio but jumps ahead of queued long-form segments, and costs 15 credits per 1000 characters. This adds substantial behavioral context without contradicting the annotations.

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 tightly written in three sentences, with the core purpose front-loaded first. Every sentence adds value: purpose, blocking/queue behavior, long-content alternative, and 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?

For a 2-parameter tool with no output schema, the description covers the essential operational context: what it does, how it behaves in relation to other audio, its cost, and when to use a different tool. Nothing critical is missing for an agent to invoke it 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 description coverage is 100%, so the schema already documents both parameters clearly: text content and voice id with default. The description adds minimal parameter-level meaning beyond labeling the call as 'short', so baseline 3 is appropriate.

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 action and resource: synthesize a short line with Paxa TTS and play it through this machine's speakers. It also explicitly differentiates from the queue_speech sibling by scoping this tool to short content, so an agent can tell them apart.

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 gives clear context for when to use speak: short lines needing immediate playback, with blocking behavior. It explicitly names the alternative for long content ('For long content use queue_speech'), satisfying the when/when-not guidance requirement.

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 description adds useful behavior beyond annotations by disclosing the credit cost and the fact that it saves a file instead of playing audio. It does not mention overwrite behavior, although destructiveHint: true already signals potential destructiveness.

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 sentences with no filler: the action is front-loaded, the file-only behavior is explicit, and the credit cost is a worthwhile addition.

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 tool with four well-documented parameters and annotations covering read/write behavior, the description is sufficient for selection and invocation. A brief pointer to list_voices or overwrite semantics would be more complete, but these are optional given the schema.

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 input schema already documents text, voice, format, and output_path. The description adds no parameter-level meaning beyond what the schema provides, matching the baseline for full coverage.

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 action: synthesize speech with Paxa TTS and save it as an audio file. The phrase 'without playing it' and the title '(file only)' distinguish it from playback-focused siblings like speak and play_audio.

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 clearly implies this tool is for file generation rather than immediate playback, and the cost note helps agents considering batch use. It does not explicitly name alternatives or say when not to use it, so it stops short of a full 5.

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, and non-destructive behavior. The description adds valuable non-structural details: the segment-sharing context requirement and the credit billing model (25 per 1000 characters, minimum 2, with context/glossary at 8 per 1000), which are not available in annotations or schema.

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 sentences with no wasted words. The main purpose is front-loaded, and the second sentence packs essential operational constraints (segment limit, billing) efficiently.

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 an 8-parameter tool, the description captures core input modes, cost model, and shared-context behavior, while high schema coverage handles the remaining parameters and annotations cover safety. A minor gap is the lack of return-shape information, but the operation is straightforward and no output schema exists.

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 88%, so the baseline is 3. The description adds meaning beyond the schema by clarifying that array input segments 'share context' and explaining the cost implications for context and glossary. This is a meaningful supplement, though formality and other parameters remain schema-only.

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 clear verb-resource pair: 'Translate text from any language into Thai.' It also names the engine (Paxa Translate) and is unmistakably distinct from sibling speech/OCR/account tools.

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?

Provides clear context: accepts a single string or up to 200 segments, making it obvious when to use this tool for Thai translation. It doesn't explicitly name alternatives or exclusions, but none of the sibling tools serve the same purpose, so there is little ambiguity.

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