Idiolect AI

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

Annotations indicate this is not read-only, and the description confirms a creation action. It adds meaningful behavioral context: it returns 'exact evidence still needed' when input is thin, and it enforces a strict policy of never inferring or scraping another person's writing. These go beyond what annotations alone convey, though it doesn't mention overwrite behavior or idempotency semantics.

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 sentences: the first states the core action and input source, the second covers edge-case behavior and a key constraint. No filler, all information is essential and 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?

With an output schema present, return values need not be detailed. The description covers the main creation behavior, the input requirements, the thin-input fallback, and a critical policy limitation. This is sufficient for an agent to understand the tool's role and constraints, especially with well-documented schema parameters.

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 baseline is 3. The description adds value by clarifying that samples and answers must be user-supplied or explicitly approved, and that insufficient input triggers a response with evidence of what's needed. This gives context to the parameters' purpose beyond their raw schema 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 clearly states the tool creates the authenticated user's Voice Profile from user-supplied or approved writing, which distinguishes it from siblings like get_my_voice (retrieval) and rewrite_in_voice (modification). The verb 'create' plus specific resource 'Voice Profile' makes the purpose 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 implies using this when creating a new profile from user's own writing, and it explicitly warns against inferring or scraping others' writing. However, it does not explicitly state how this differs from rewriting or getting an existing profile, so it lacks clear exclusions.

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 annotations already indicate a non-read-only operation, and the description adds meaningful behavioral detail: it returns a Voice Match only under eligibility conditions and provides explicit metric provenance. This goes beyond the annotation flags, though it does not disclose potential side effects like credit usage.

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 concise, with two sentences that front-load the core action and then describe the return condition. No wasted words or repetition of schema 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?

Given the output schema, annotations, and high parameter coverage, the description is adequate for tool selection and invocation. It alludes to prerequisites like a saved corpus and eligibility, which are important, but it does not elaborate on them, leaving slight ambiguity for a complex tool.

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 schema covers 100% of the parameters with clear descriptions for 'brief' and 'format'. The tool description adds the framing of a 'supplied brief' and mentions the selected voice, but it does not provide new parameter-level meaning beyond what the schema already offers.

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 action ('Draft new prose') and the resource ('in the selected voice from a supplied brief'), distinguishing it from sibling tools like 'rewrite_in_voice' which would handle existing prose. The return behavior is also mentioned, making the tool's purpose 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 for when to use the tool: when you have a brief and need new prose in a saved voice. It does not explicitly name alternatives or exclusions, but the context is sufficient to differentiate it from rewriting or creating a voice profile.

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 cover read-only, idempotent, and non-destructive hints. The description adds useful beta-specific behavior (balance is a preview, not consumed by drafting) that goes beyond the annotations. No contradiction.

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 only: the first states the core purpose, the second provides relevant beta context. No fluff, front-loaded, and every word 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?

With an output schema present and no parameters, the description covers the purpose and the only relevant nuance (beta behavior). It is complete for a simple status-check tool.

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 coverage is 100%. The description does not need to explain parameters; the baseline for zero-parameter tools is 4, which is appropriate here.

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 'Return the authenticated account's generation access and credit balance' with a specific verb and resource. It clearly differentiates from sibling voice-related tools by focusing on account status.

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 about when the balance matters ('During the free beta, the balance is a preview and drafting does not use it'), implying the tool is for checking access/credit rather than voice operations. It does not explicitly name alternatives, but the context is sufficient.

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 some context by stating the purpose ('so you write as them') and implies it is a load operation, but it does not disclose side effects, permissions, or other behavioral traits beyond the annotations. The annotations are all false, offering little safety guidance, and the description does not elaborate.

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 sentences, front-loaded with the most important usage context ('Use this when...') and immediately explains the effect. Every word earns its place, with no redundancy or irrelevant detail.

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 tool is simple (no parameters) and an output schema exists, so the description need not explain return values. The description provides sufficient context by stating the trigger for use and the intended outcome, making it complete for an agent to select and invoke 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?

With zero parameters, the schema already provides complete coverage. The description does not introduce any parameter-related information, but since there are no parameters, the baseline of 4 applies as per the rubric.

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 tool loads the user's Idiolect AI voice, with a specific verb ('loads') and resource ('user's Idiolect AI voice'). It also differentiates from siblings by explicitly framing its use as preparation for writing on the user's behalf, which is distinct from drafting, rewriting, or scoring.

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 explicitly states when to use this tool ('when you are about to write anything on the user's behalf'), providing clear context. However, it does not mention when not to use it or explicitly name alternatives among the sibling tools, so it falls short of 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 indicate the tool is not read-only and not destructive. The description adds meaningful behavioral context by disclosing that it returns a safety recommendation, a candidate, and a diagnostic delta, and that it retains the original if the candidate regresses. This fallback behavior is not encoded in 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?

Two concise sentences: the first states the primary function, the second explains the return behavior. Every word earns its place, with no redundancy or fluff.

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 only two parameters and an output schema, the description covers purpose, return behavior, and regression handling sufficiently. It does not mention that a voice profile must be created beforehand (via create_my_voice), but this is a minor gap given the overall completeness and the existence of sibling tools implying this prerequisite.

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 schema fully documents both parameters (text and targetRegister) with descriptions and enum values, achieving 100% coverage. The description adds little beyond 'selected voice' hinting at the user's voice, but the schema already explains that the voice is the user's and the targetRegister adapts format. 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 uses the specific verb 'rewrite' with a clear resource ('supplied prose') and scope ('in the selected voice'), making the tool's function immediately obvious. It additionally clarifies the output includes a safety recommendation, which distinguishes it from sibling tools like draft_in_voice that generate new prose.

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 clearly implies the tool is for reworking existing prose rather than generating new drafts, providing useful context for when to use it. However, it does not explicitly mention alternatives or state when not to use it, so it lacks explicit exclusions that would merit a perfect score.

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 behavioral context beyond annotations: it explains the conditional nature of the result ('only when eligible') and mentions 'safe evidence provenance'. However, it does not clarify whether this is a read-only operation or if there are side effects, and terms like 'unmeasured reason' and 'safe evidence provenance' are vague. Annotations provide no safety hints (all false), so the description carries some burden but leaves gaps.

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 exactly two sentences, with the first stating purpose and the second adding a key behavioral detail. No redundant words, front-loaded with the primary action. Efficient and well-structured.

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?

Given the tool has an output schema (unknown content) and only one parameter, the description is reasonably complete. It explains the tool's purpose and a critical conditional behavior. It could be more explicit about prerequisites (e.g., needing a saved voice) but that is arguably implied by 'saved corpus' and sibling tools like 'create_my_voice'.

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 schema description covers the only parameter 'text' with 'Text to score against the user's voice.' The tool description does not add semantic meaning beyond this; it merely refers to 'candidate prose' synonymously. With 100% schema coverage, 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 clearly states the tool's function: 'Check how close candidate prose is to the selected voice.' This is a specific verb ('check') and resource ('candidate prose' vs 'selected voice'), which clearly differentiates it from siblings like 'create_my_voice' or 'rewrite_in_voice'. 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 implies the tool should be used when you need to evaluate prose against a voice, but it does not explicitly mention when not to use it or contrast it with alternatives. It discusses eligibility conditions ('Returns Voice Match only when the saved corpus and candidate are eligible') but offers no direct comparison to sibling tools.

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