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

With no annotations present, the description carries the full burden and does disclose an important behavioral trait: changes are session-scoped and 'persist until the MCP server restarts'. That volatility disclosure plus the no-arg read mode is meaningful. It still omits what happens to in-flight or subsequent speech and how invalid values are handled, so it is strong but not exhaustive.

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, front-loaded with the core action, followed by the persistence caveat and the read-only invocation mode. Every sentence earns its place with no filler.

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 six-parameter, all-optional configuration tool with no output schema, the description covers scope, lifetime and the zero-argument read behavior, which is what an agent needs to call it safely. It is slightly incomplete on the relationship to the 'speech_style' sibling tool and on interaction with active speech.

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 every one of the six parameters (rate, voice, engine, openai_model, openai_voice, speech_style) is documented in the schema with defaults, ranges and examples. The description adds no parameter-level detail beyond the schema, so the baseline 3 is correct.

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 ('Set default speech preferences') with a clear scope ('for this session'), so an agent knows exactly what the tool mutates. It does not, however, distinguish itself from the sibling 'speech_style' tool or explain how a 'default preference' differs from a per-call style, leaving some ambiguity among siblings.

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 one concrete usage rule ('Call with no arguments to view current config'), which is genuinely useful dual-mode guidance. But it offers no when-not guidance and never routes the agent away from the closely named sibling 'speech_style', so selection between the two remains implied rather than 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. It usefully discloses that results vary by engine and include macOS system voices and/or OpenAI voices, but it does not describe the return format (e.g., names vs. IDs vs. metadata) or any other behavioral trait beyond that.

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 core purpose is front-loaded, followed by the one important behavioral dependency.

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 read-only listing tool with a fully documented single parameter and no output schema, the description is nearly complete. It states purpose and return variation, though it could have added a brief note on when to call it before using speak.

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 single enum parameter is fully documented in the schema. The description mentions the engine parameter but adds no syntax or meaning beyond what the schema already provides, 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 verb ('List') and resource ('available text-to-speech voices'), making the tool's purpose immediately clear. It does not explicitly differentiate itself from siblings like speak or configure_speech, but the listing purpose is distinct enough on its own.

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 no guidance on when to use this tool versus alternatives such as speak or configure_speech. It only explains how the engine parameter affects the result, which is parameter behavior rather than tool-selection 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?

With no annotations, the description carries the burden and does well: it discloses non-blocking behavior ('returns immediately without waiting for speech to finish'), that audio plays on the user's machine, the default offline engine, and the OPENAI_API_KEY requirement. It omits failure behavior (e.g., what happens if the key is missing) and whether speech can be interrupted.

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?

Front-loaded purpose in the first clause, then usage, then behavior. Three short paragraphs with no filler; each sentence contributes routing or behavioral 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 3-param, no-annotation, no-output-schema tool, the description covers purpose, usage, non-blocking behavior, engine choice, and the API-key prerequisite. Only error/failure handling is left uncovered, which is a minor gap.

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 all three parameters, making 3 the baseline. The description adds the default engine and the free-vs-premium tradeoff, but it also states 'Default engine is macOS system TTS' while the schema says 'Defaults to session config' – a mild inconsistency rather than a clarifying addition.

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: 'Speak text aloud using text-to-speech.' That is unambiguous and distinct from the sibling tools (list_voices, configure_speech, speech_style), but the description never names those siblings or clarifies the boundary, so an agent must infer the routing.

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?

Gives concrete when-to-use context: 'summarize changes, announce completions, or narrate explanations audibly.' That is clear positive guidance, but there is no exclusion guidance (e.g., when not to speak, or to use configure_speech first).

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 disclose the key non-obvious behavior: the style affects the pre-TTS composition of summaries rather than the voice itself, and the empty-string sentinel clears state. It omits persistence scope (session vs global), whether setting is idempotent, and any auth requirements.

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 blocks: the core behavior plus its negative boundary first, then concrete examples, then the control semantics. Every sentence earns its place and the most important clarifier (not the TTS voice) is front-loaded.

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 one-parameter tool with no output schema and no annotations, the description covers purpose, examples, and state-clear/view behavior well enough to invoke correctly. The remaining gap is scope/persistence of the setting and what the view mode returns, which are minor for this complexity.

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 single parameter is fully documented in the schema, so the schema does the heavy lifting. The description restates the same clear/view semantics in prose and adds only the illustrative examples, 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?

States a specific verb and resource ('Set a speaking style or persona') and immediately bounds the effect: it shapes how spoken text is composed, not the TTS voice. That boundary functionally separates it from the voice-related siblings (speak, list_voices, configure_speech) without the agent needing to open any schema.

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?

Gives explicit mode-selection instructions: pass a style to set it, pass an empty string to clear it, omit the argument to view the current style. This is clear context for using the tool, though it never states when to reach for this tool rather than configure_speech, nor any prerequisite conditions.

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