RPCS-1 Agent Tuner & Translation Bridge

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description adds further behavioral clarity: 'Deterministic and stateless — nothing is stored server-side.' It also explains the two-phase interaction pattern and the precise output semantics (continuous 0-100 values, never categorical labels). This is valuable context beyond the structured annotations and no output schema is present, so the description carries the burden well.

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 yet information-dense, using four sentences to cover purpose, usage, integration, and behavior. It is front-loaded with the most important action and output constraints, then flows logically into invocation, storage, and determinism. No redundant filler or repetition of schema details.

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's moderate complexity, one optional parameter, and no output schema, the description adequately covers the full interaction contract: how to request questions, how to submit answers, what the output profile is, what to do with it, and backend behavior. It also includes a schema URL for further reference. The context is complete for an agent to select and invoke the 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 description coverage is 100%: the answers object documents each primitive and its a/b/c enum, and the schema description says 'Omit entirely to receive the questions.' The tool description adds meaning by explaining what the answers represent behaviorally and how they map to a continuous profile. It doesn't need to repeat schema details, and it supplements with the two-mode semantic difference, so a strong score is warranted.

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: 'Build a ReceiverProfile (TI, SG, FT, UE, AR — continuous 0-100, never a category label) from five behavioral forced-choice answers.' This clearly distinguishes calibrate_profile from siblings like interpret or normalize by describing its unique role in constructing a receiver profile. It also explains the two invocation modes (no answers vs. with answers), further clarifying purpose.

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?

Explicit usage instructions are provided: 'Call with NO answers to get the five questions to ask the user; call again with their answers (a/b/c per primitive) to get the profile.' It also states when the output should be used: 'Store the returned profile JSON in the user’s notes or memory and pass it to render_reply / prepare_prompt on every turn.' This gives clear when-to-use and integration guidance beyond what schema or sibling names imply.

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=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. The description adds meaningful behavioral detail about outputs (AR level, confidence, candidate interpretations, clarifying questions, suggested next step), which goes beyond the annotations and helps set expectations.

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 and well-structured: a first sentence states the core purpose and framework, a second lists key outputs, and a final clause gives a concrete trigger condition. No wasted words, and the most important information 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?

With no output schema, the description appropriately enumerates the main return fields (AR level, confidence, candidates, questions, next step). It also gives usage context. It could optionally clarify how the 'risk' parameter affects thresholding, but the schema already explains the parameter options, leaving the description sufficient for basic selection and invocation.

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%, with both 'text' and 'risk' parameters fully described in the schema. The description does not add significant parameter-level semantics beyond what the schema provides, so the baseline score of 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?

Clearly states the tool's verb ('Detect ambiguity') and resource ('user messages'), and names the specific framework (RPCS-1 Signature Ambiguity Framework). It differentiates from siblings like 'rewrite' or 'normalize' by focusing on ambiguity detection and producing interpretation artifacts.

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 explicit guidance on when to use ('Use when a user says something vague, passive-aggressive, or underspecified'). It does not mention when not to use it or explicitly name alternatives, but the use context is clear enough to guide selection.

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: true, idempotentHint: true, and destructiveHint: false, covering the safety profile. The description adds minimal behavioral context beyond what the annotations provide; it mentions the transformation but not details about output format or edge cases.

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 with no redundant phrasing. It front-loads the primary action and adds a usage condition, every word earning 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?

For a simple one-parameter tool with strong annotations, the description is adequate. It explains what the tool does and when to use it. The lack of an output schema is mitigated by the phrase 'into coherent prose,' hinting at the return value, though an explicit output type would improve completeness.

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% (the 'text' parameter is described as 'Fragmented text to normalize'). The description enriches this by specifying what fragmented text looks like: ellipses, fragments, and run-on thoughts. This adds meaning beyond the schema, so a score above baseline is warranted.

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: 'Clean up text with ellipses, fragments, and run-on thoughts into coherent prose.' This provides a specific verb and resource. It does not explicitly distinguish from the sibling tool 'rewrite', but the focus on fragmented input implicitly differentiates it.

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 'Use when a user types stream-of-consciousness or fragmented input,' giving clear context for when to apply the tool. It does not mention when not to use it or alternatives, so it falls short of a 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 cover readOnly, idempotent, and non-destructive behavior. The description adds meaningful context about lexical/structural detectors, return contents, and the authoritative role of route_intent. No contradiction with 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?

Three sentences, each serving a distinct purpose: definition, usage instruction, and scope caveat. No filler, though slightly dense and could be tightened.

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?

No output schema exists, so the description compensates by listing return items (recovered intent, canonical translation, ambiguity level, clarify/commit decision). It also names related tools and clarifies authority relationships, making the tool's role sufficiently complete.

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 baseline is 3. The description adds some context ('possibly ambiguous, fragmented, or underspecified') but does not significantly extend beyond the schema's own parameter descriptions.

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?

Description clearly states prepare_prompt is the inbound half of the Translation Bridge loop, taking the raw message and ReceiverProfile and returning recovered intent, canonical translation, ambiguity level, and clarify-vs-commit. It distinguishes itself from route_intent by delegating the final decision to that sibling tool.

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?

Explicitly instructs to 'Call this before acting on any ambiguous user request' and provides a scope note naming route_intent as the authority for commit-vs-clarify decisions, including what to do when they disagree. This is direct when-to-use/alternative 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?

Annotations already state readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context: 'Deterministic, stateless, read-only — does not store past recommendations' and explains fallback behavior for unknown models. This goes beyond the annotations, providing a clear behavioral profile.

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 composed of four sentences, each adding distinct value: purpose, input/output summary, optional parameter behavior, and determinism/statelessness. The information is front-loaded with the main purpose in the first sentence, and every sentence earns its place without redundancy.

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's complexity, the description covers the environment inputs, target_model behavior, and output summary, while the output schema handles return value details. However, it never explicitly mentions the 'task' parameter, relying on schema defaults and property descriptions to fill that gap. This is adequate but not fully complete for a tool with multiple nested objects.

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 coverage is 50% (target_model and target_platform have descriptions, while task and environment lack top-level descriptions). The description partially compensates by naming the environment factors (entropy, predictability, stakes, context horizon, commitment style) and explaining target_model's E-LIT table behavior, but it omits any explanation of the 'task' parameter and target_platform, leaving a significant 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 opens with a clear verb+resource ('Diagnose why a deployed AI agent may fail') and then enumerates specific inputs and outputs, including receiver profile values, platform parameters, and regime prediction. This clearly distinguishes the tool from siblings like calibrate_profile or interpret, which focus on other aspects of agent behavior.

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 a clear context for use: diagnosing why a deployed AI agent may fail. It also provides optional usage guidance with target_model. However, it does not explicitly compare with sibling tools such as calibrate_profile or prepare_prompt, nor does it state when not to use this tool, so it lacks exclusionary 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?

Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds context by explaining that the tool is deterministic and returns instructions with a 'why-trace,' which further clarifies the read-only, repeatable nature. It does not contradict 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 three sentences, front-loaded with the core purpose, and every sentence earns its place. It provides the overall role, inputs/outputs, and a concrete action item without any 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?

Despite having no output schema, the description thoroughly explains what the returned instructions cover (structure, warmth, explicitness, revision posture, ambiguity handling) and how to apply them. It also mentions the prerequisite of a calibrated user, connecting to sibling tools in the flow.

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 are fully documented. The description merely refers to 'draft reply' and 'user's ReceiverProfile,' which restates the schema. No additional semantic details or examples are provided 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 identifies the tool as 'The outbound half of the Translation Bridge loop' and specifies exactly what it does: takes a draft reply and ReceiverProfile, then returns deterministic rendering instructions. It uses a specific verb ('takes... and returns') and distinguishes this tool from siblings by naming its role in the loop.

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 the tool: 'Call this on every reply to a calibrated user.' It also instructs to 'Apply the instructions to your draft before answering.' While it doesn't mention when-not-to-use or name alternatives, the placement in the loop makes the usage context 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. Description adds behavioral context by stating the tool returns 'rewrite instructions' and lists the style enum, which goes beyond schema. No contradiction with 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?

Single sentence, front-loaded with the core action, and the style list is compact. No wasted words.

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 annotations, the description is largely sufficient. However, it introduces ambiguity by saying 'Get rewrite instructions' versus the title's 'Rewrite text', leaving uncertainty about whether the output is rewritten text or instructions about rewriting. No output schema exists, so this ambiguity is not resolved.

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 covers 100% of parameters (text and style) with descriptions and enum values. The description's mention of styles is redundant with the schema's enum, so it adds no additional semantic 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?

Description explicitly states 'Get rewrite instructions for adapting text to a specific style' with a clear verb and resource. It lists six target styles, distinguishing it from sibling tools that focus on interpretation or normalization. The use case 'tone adjustment' further differentiates it.

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?

'Use when communication needs tone adjustment' provides an explicit condition for when to invoke the tool. It doesn't name alternatives or state when not to use it, hence a 4 rather than 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 readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds that the tool is 'deterministic, stateless, read-only' and mentions benchmarks, providing context beyond annotations without 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?

The description is somewhat long but packs essential details; every sentence earns its place. Could tighten a bit, but structure front-loads purpose and then provides specifics without redundancy.

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?

Despite no output schema, the description covers return decisions (commit, commit_with_note, present_options, clarify), fallback behavior, and the role of ReceiverProfile. Given tool complexity (4 params, nested objects), this is complete and actionable.

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%, but the description significantly enriches parameter meaning: explains the purpose of hypotheses (with likelihoods and paraphrases), why paraphrases matter for user verification, and how profile dimensions affect thresholds. This goes well beyond schema descriptions.

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 explicitly states the tool's role: 'Entropy routing over competing interpretations' and 'this tool is the commit-vs-clarify AUTHORITY in the pipeline.' It clearly differentiates from siblings like interpret or normalize.

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 tells when to use (ambiguous requests, generating hypotheses) and when not to ('do not use the fallback for interpreting arbitrary sentences'). It also references the sibling tool calibrate_profile for profile setup.

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