rtcf

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

No annotations are provided, so the description must carry the behavioral burden. It states the tool composes a prompt but does not disclose any additional behavior such as validation, length constraints beyond what the schema already provides, or the output format. The description is adequate but could offer more context.

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 long, front-loaded with the core action, and contains no redundant information. Every sentence 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?

Given the simplicity of the tool (4 string parameters, no output schema), the description explains the input structure and the output (ready-to-use prompt). It could explicitly mention the output is a string, but the context is sufficient for correct use.

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 does not add any semantics beyond what the schema's individual parameter descriptions provide. It only groups the parameters into categories (Role, Task, Context, Format), which adds minimal value.

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 composes a prompt from explicit parts (Role, Task, Context, Format) and distinguishes it from the sibling 'improve_prompt' by specifying use when the user already knows the pieces.

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 says when to use this tool ('when the user already knows the pieces and wants them woven'), implying that for improving existing prompts the sibling should be used. It does not explicitly state when not to use, but the guidance is clear.

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 carries the behavioral disclosure burden. It clearly explains that the tool returns a short, ready-to-send continuation message that anchors to existing work, and it adds the API key requirement. It does not detail edge-case behavior or output formatting beyond this, but the core invocation-relevant behavior is transparent.

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 compact and front-loaded: the core purpose, usage boundary, return behavior, and access requirement each get one sentence with no filler. Every sentence earns its place and supports selection or invocation.

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 generative tool with no output schema, the description provides enough context to invoke it correctly: what it returns, when to use it, when not to use it, how it differs from improve_prompt, and that an API key must be appended to the connector URL. The schema covers the parameters, so the description does not need to repeat them.

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 parameters next_request, original_goal, and conversation_summary already carry clear meaning. The description adds overall context about follow-up generation and the tool not restarting work, but it does not add much per-parameter detail beyond what the schema already provides. The 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 and resource: it writes the user's next follow-up message for an in-progress conversation. It also distinguishes itself from sibling tools by saying it is not for brand-new tasks, and specifically names improve_prompt as the alternative.

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 explicit when-to-use and when-not-to-use guidance: use it to 'refine, deepen, or continue earlier work,' and avoid it for 'a brand-new task' where improve_prompt should be used instead. This clearly routes an agent to the correct sibling.

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 behavioral burden: it explains that the tool rewrites a prompt, returns the improved prompt and parts, and provides clarifying questions and model recommendations. The phrase 'use this before answering' communicates that this is an intermediate compilation step; no side effects or risks are materially unaddressed.

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 focused sentences with the core purpose front-loaded. Every sentence contributes actionable information: what it does, what it returns, and when to invoke it.

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?

Coverage is complete for a low-risk rewriting tool: input is fully schema-described, return content is listed, and trigger conditions are stated. It stops short of fully disambiguating build_prompt and improve_followup, but the overall definition is sufficient without an output 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%: both prompt and target are already described accurately in the input schema. The tool description adds RTCF and output context but no new parameter-level semantics, so the baseline of 3 applies.

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: it rewrites a rough prompt into a sharper ready-to-use prompt structured as Role, Task, Context, Format. It also lists the returned components, which adds precision and clearly distinguishes it in intent from build_prompt, though it does not name or differentiate intruments directly.

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 explicit when-to-use triggers: 'when the user's request is vague, or when the user asks to improve a prompt.' It does not provide when-not-to-use guidance or direct the agent to build_prompt/improve_followup, but the stated conditions are clear enough for normal selection.

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