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 valuable context: it returns an 'advisory Stop-hook decision' and explicitly says it 'runs no commands', which clarifies its non-execution nature. This goes beyond the annotations without contradicting them.

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 wasted words. It front-loads the purpose and includes the key behavioral note (advisory, runs no commands). It is concise and well-structured for a tool of this complexity.

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?

While the purpose and non-execution behavior are clear, the description omits any detail about the input parameters (especially 'final_message') and the exact structure of the advisory decision. Since there is no output schema and no parameter descriptions in the schema, the description should explain what an agent needs to supply and what it will receive. It does not, making the tool incomplete for correct 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?

The schema description coverage is 0%, so the description must compensate by explaining the parameters. It does not. The description only says 'supplied transcript', which vaguely maps to the 'messages' array but does not clarify the role of 'final_message'. An agent cannot infer the meaning or format of these parameters from the description, leaving a significant gap for a tool with only two 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 states a specific verb ('Judge') and a specific resource ('supplied transcript') with a clear purpose ('makes unsupported completion claims'). It also notes the return is an 'advisory Stop-hook decision' and that it 'runs no commands', which helps set it apart from some sibling tools. However, it does not explicitly distinguish itself from the many system_one_* siblings, so it loses a point for lacking differentiation.

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 usage (judging completion claims in a transcript) but provides no explicit when-to-use guidance or alternatives. Given the large sibling set (system_one_gate, system_one_review, system_one_verify, etc.), it does not state when this tool is preferred over others. The purpose is clear enough to infer a use case, but it does not actively guide the agent toward this tool vs. alternatives.

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, covering the safety profile. The description adds that ambiguous results require review, which is a useful behavioral cue beyond annotations. However, it does not elaborate on what 'review' entails or other potential side effects, so the added value is moderate.

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, front-loaded sentence with no redundant words. It states the core action and a key behavioral caveat efficiently, earning a top score for conciseness and structure.

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 5 parameters, no output schema, and zero parameter descriptions in the schema, the description must carry substantial load. It leaves the purpose or intent of parameters like auto_accept and minimum_margin entirely unaddressed. An agent would not know how to set these values correctly, making the definition critically incomplete.

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 0% for all 5 parameters. The description only implicitly references 'items' and 'classes' (via 'supplied items' and 'class catalog'), but says nothing about purpose, auto_accept, or minimum_margin. These parameters remain entirely unexplained, so the description fails to compensate for the schema's lack of 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 states a clear verb and resource ('Classify supplied items against a shared class catalog'), and the name itself is unambiguous. It does not explicitly compare to sibling tools like system_one_decide or system_one_rerank, but the term 'classify' is self-explanatory and distinct enough.

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 phrase 'ambiguous results require review' implies a follow-up action but does not specify when to prefer this tool over siblings or mention any alternative tool names. It offers some contextual guidance but lacks explicit exclusions or routing logic, so an agent must infer usage.

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, and the description reinforces these with 'never modifies host files' and 'returns a new transcript'. It adds the behavioral details of verbatim processing and output creation beyond the structural annotations. No contradiction exists.

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 concise sentence with no redundant phrasing. It front-loads the primary action, states the return result, and explicitly addresses side effects in a compact way. Every clause 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?

For a tool with a nested options object, seven undocumented parameters, and no output schema, the description is too thin to fully orient an agent. It omits what goal is for, how options affect behavior, and what the returned transcript contains beyond being 'new'. The complexity of the schema demands more explanatory context than a single sentence provides.

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 0%, so the description must compensate, but it only loosely references 'supplied canonical messages' without explaining goal, options, or the nested option semantics. The nested options object contains seven tunable parameters with meaningful constraints, none of which are addressed. This is a clear gap for a tool with undocumented 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 names a specific verb, 'compact', a resource, 'supplied canonical messages', and a clear outcome: 'returns a new transcript'. It is understandable and distinguishable from siblings by the 'compact' operation, though the phrase 'tool-pair compaction' is jargon-heavy and does not fully define what the compaction accomplishes.

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 any of the 13 siblings. It does not state preconditions, alternatives, or exclusions. The only contextual hint is 'supplied canonical messages', which implies a specific input source but is not actionable routing 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 cover readOnlyHint, idempotentHint, and destructiveHint, so the description adds value with the caveat that agreement is not evidence of truth. This is a useful interpretive note. However, it does not disclose return format, pagination, or any other behavioral traits, leaving gaps despite the annotation coverage.

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 fluff. The purpose is stated first, followed by a crucial caveat. This is maximally concise and well-structured for the information it conveys.

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 4 parameters, no output schema, and 0% schema description coverage, the description is inadequate. It omits explanations for auto_accept, what aspects should be, the return value, and any prerequisites. The annotation safety profile helps, but the description leaves too much unexplained for an agent to call 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 0%, so the description must explain parameters. It hints at passage_a, passage_b, and aspects ('two passages', 'by aspect'), but does not clarify the meaning of 'aspects' or explain auto_accept at all. The auto_accept parameter is entirely undocumented, 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 clearly states the tool compares two passages, both overall and by aspect. The verb 'compare' and resource 'two passages' are specific, and the mention of 'by aspect' adds nuance. It distinguishes from siblings like extract or classify, though it could be more explicit about what comparison entails (similarity vs difference).

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?

No guidance is given on when to use this tool versus the many siblings (system_one_belay, system_one_verify, etc.). There is no mention of prerequisites, context, or alternative tools. The agent must infer usage from the name alone, which is insufficient.

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, so the safe, non-mutating nature is clear. The description adds that it is advisory only and does not act on the decision, which reinforces the annotations without contradicting them. However, it doesn't detail side effects (none expected) or response format, but annotations cover the safety 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 a single sentence with no waste: it states the core purpose (compare candidates) and a critical caveat (advisory only). All key information is front-loaded and concise.

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 7 parameters and no output schema, the description leaves out return format and details on how parameters like evidence and auto_accept are used. However, it's a decision-support tool with clear advisory role, and the schema provides structural limits (2–6 candidates, max requirements). Some gap exists in explaining the decision process, but it's sufficient for a competent 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?

Schema description coverage is 0%, so the description must add meaning to parameters. The description mentions 'candidates', 'explicit requirements', and 'escape hatches', which aligns with parameters like candidates, requirements, and escape_hatches, but doesn't explain other parameters like evidence, priorities, or auto_accept. It provides minimal compensation for the lack of schema descriptions, so a 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 it compares 2–6 candidates with explicit requirements and escape hatches, which is specific and conveys the resource (candidates) and action (compare/decide). It also notes it's advisory only, which distinguishes it from tools that act. However, it doesn't explicitly name sibling tools it differs from, but the advisory-only qualifier helps differentiate from gate/verify.

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 usage when comparing candidates and making a decision, but does not explicitly state when to use this vs alternatives like system_one_compare or system_one_review, nor when not to use it (e.g., for acting on decisions). It also doesn't describe prerequisites like providing evidence or candidates beyond the schema.

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 safety (readOnlyHint, destructiveHint), so the description's job is to add behavioral context. It adds the important constraint 'Never generates extracted values,' clarifying that it only returns verbatim matches. This adds value beyond the annotations, though it doesn't cover all edge cases like no-match behavior.

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 at two sentences, with the primary action front-loaded. Every word serves a purpose, and there is no redundant fluff. It efficiently conveys the core behavior in minimal space.

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 (4 parameters, no output schema, no parameter descriptions), the description is far from complete. It does not explain what the tool returns, how parameters are used, or what 'bounded' means in this context. An agent would have many open questions when attempting 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 0%, so the description must compensate by explaining parameters. It fails to do so—no mention of 'document', 'fields', 'auto_accept', or 'minimum_margin'. The mention of 'regex' hints at the pattern field, but this is insufficient for an agent to understand how to fill the inputs 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 clearly states the tool's function: it finds bounded regex candidates and selects verbatim substrings. It uses specific verbs and a clear resource, distinguishing it from generic operations. However, it does not explicitly differentiate from sibling tools, so a perfect score is not warranted.

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 a use case for extraction from documents via regex, but it provides no explicit guidance on when to use this tool versus the many sibling tools. There are no when-not conditions or named alternatives, leaving usage partly inferred.

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 the operation read-only, idempotent, and non-destructive. The description adds meaningful behavioral context beyond those annotations: it reveals an implementation trait ('without embeddings') and what the caller should expect back ('ranked candidates and an existence judgment'). It does not cover failure modes or edge cases, but the annotation safety profile lowers the bar.

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 filler, front-loading the core verb 'Find' and the key scoping phrase 'supplied candidates.' Every part adds useful information: the operation, the non-embedding constraint, the ranking behavior, and the existence judgment.

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 at least names the two expected outputs, which is helpful. Still, it does not define what 'existence judgment' means, how 'ranked candidates' are ordered, or how top_k interacts with results. The description is adequate for basic routing but not fully complete for a tool with no 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 0%, so the description carries the full burden of explaining parameters. It implicitly covers 'query' and 'candidates' but says nothing about the optional 'top_k' parameter or the purpose of candidate 'id' and 'text' fields. With three parameters and zero schema descriptions, this is a meaningful 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 identifies a specific verb-resource pair: 'Find which supplied candidates answer a query' and adds a distinctive output, 'ranked candidates and an existence judgment.' It also mentions 'without embeddings,' which helps separate it from embedding-based sibling tools. However, it does not explicitly name or contrast any sibling like system_one_rerank, so differentiation is implied rather than explicit.

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 phrase 'without embeddings' implies a use case where embeddings are unavailable or undesired, giving some contextual guidance. But the description does not state when to prefer this tool over siblings such as system_one_rerank or system_one_compare, nor does it mention exclusions. Usage is implied rather than clearly routed.

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 behavior, so the safety profile is clear. The description adds behavioral context beyond annotations: the operation is bounded and it intentionally does not execute tests. 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?

Two sentences, each earning its place: the first states the combined purpose Discipline, the second prevents a common misuse. Some jargon like 'System One' and 'bounded' is unexplained, but overall it is compact 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?

For a tool with 9 parameters, nested object evidence, no output schema, and 0% parameter documentation, this description is under-specified. An agent cannot infer how evidence should be structured, what thresholds like auto_accept or composite_floor do, or what response to expect.

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 0%, so the description must carry parameter meaning, but it only adds semantics for diff and claims, and indirectly tests. The critical params request, evidence, review_at, auto_accept, composite_floor, and context remain entirely unexplained.

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 pairing: 'Review a diff and verify completion claims' in one request Dropping. It distinguishes itself from a test-runner by explicitly saying it does not execute tests. However, it does not differentiate clearly from system_one_review or system_one_verify beyond the 'together' phrasing.

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 when to use it ('together in one bounded System One request') and states an exclusion ('Does not execute tests'). It does not name alternatives or provide explicit when-to-use/when-not-to-use guidance relative to the 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=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no meaningful behavioral context beyond the annotations; 'Validated raw System One request' is unclear and does not disclose any side effects, return format, or error behavior. It does not contradict annotations, but it also does not enrich them.

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 short, but this is under-specification rather than conciseness. It fails to convey essential information in the limited space, so the brevity is not a strength.

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 three parameters, no output schema, and zero schema coverage, the description is wholly inadequate. An agent has no idea what the tool does, how to format the request, or what to expect in response. This is a complex query tool that requires substantial documentation.

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 0%, so the description must explain the parameters, but it says nothing about 'state', 'questions', or 'model'. The schema only lists them as required/optional with basic types, but no semantic meaning is provided. The agent cannot infer what values to pass or how they affect the request.

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 says 'Validated raw System One request' but does not state what the tool actually does with the state and questions. It is not a tautology, but it is vague and does not clearly identify the operation or distinguish it from the many sibling tools. The negative clarification about OpenAI chat-completions does not define the tool's 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?

There is no guidance on when to use this tool versus its siblings. The only hint is a negative statement ('not an OpenAI chat-completions endpoint'), which does not help an agent decide when to call this tool. No context, prerequisites, or alternative routing is provided.

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 a behavioral nuance beyond annotations: scoring is independent per candidate, and tie-breaking uses original candidate order. This adds value beyond the readOnly and idempotent hints. However, it does not mention output format or any side effects (e.g., whether scores are returned), which could be useful but is not critical given 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, front-loaded sentence that immediately states the core action and a key behavioral rule. Every word earns its place; there is no filler or redundant phrasing.

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 three parameters, no output schema, and zero parameter descriptions, the description leaves out essential context. It does not explain the return value (sorted list? scores? both?), the meaning or effect of top_k, or any constraints on candidate structure beyond what the schema shows. An agent cannot fully predict the tool's behavior from this description alone.

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 0%, so the description must compensate. It implies the roles of query and candidates through 'score relevance' and 'each supplied candidate,' but it does not explicitly explain them, nor does it mention the optional top_k parameter at all. The agent gets no information about what top_k controls or how to use it, making parameter semantics incomplete.

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: independently score each candidate's relevance, then sort, with tie-breaking by original order. This clearly distinguishes it from sibling tools like system_one_compare (comparison) or system_one_extract (extraction), giving an agent an unambiguous sense of 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 provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites or exclusions. It only states what the tool does, leaving the agent to infer the appropriate context from the name alone. There is no explicit 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?

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the non-mutating and idempotent nature. The description adds specificity by stating it does not execute tests or apply patches, which is a more detailed behavioral constraint than the generic read-only hint. It also aligns with the annotations without contradiction, reinforcing the safety 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 extremely concise: two sentences with zero filler. The primary purpose is front-loaded in the first sentence, and the second sentence adds a critical exclusion (does not execute tests or apply patches) that clarifies scope. Every word earns its place, making it easy to parse quickly.

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 being concise, the description is incomplete for a tool with 7 parameters, no output schema, and no parameter explanations. It lists review criteria but does not explain how they are scored, what the output format is, or how optional parameters like review_at, auto_accept, and composite_floor influence behavior. An agent would lack sufficient context to invoke the tool correctly beyond the simplest case.

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 0%, meaning none of the 7 parameters are described in the schema itself. The description mentions 'diff' implicitly by saying 'proposed diff', but it does not explain the meaning, purpose, or constraints of any parameter (request, tests, context, review_at, auto_accept, composite_floor). The description fails to compensate for the lack of schema documentation, leaving agents guessing about parameter semantics.

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 action: 'Score a proposed diff' and specifies the criteria (correctness, spec match, test gap, blast radius, safety). It also explicitly notes what it does not do ('Does not execute tests or apply patches'), which helps distinguish it from potential execution-oriented tools. The verb+resource is specific and 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 a hint about when to use this tool by stating it does not execute tests or apply patches, implying it is for static review only. However, it does not name specific sibling tools or provide explicit guidance on when to choose this over alternatives like system_one_verify or system_one_gate. The usage context is only implied, not fully articulated.

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 establish readOnlyHint and idempotentHint, and the description adds a valuable safety boundary: 'Never executes or fetches the text.' This tells the agent the tool analyzes the supplied text without making network calls or running content, which is behavior beyond what the annotations alone state.

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 short sentences deliver the core purpose and a critical negative guarantee with no filler. The key verb and object appear first, making the definition easy to process quickly.

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 has four parametersasia and no output schema, and the description leaves purpose, block_at, and review_at undefined while also not explaining the result format of the screening. The definition is enough to call the tool with just text, but not enough for an agent to use the optional controls or interpret the response confidently.

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 0%, so the description must compensate, but it only references 'text' and leaves purpose, block_at, and review_at entirely unexplained. It adds the useful idea that text is external/unsafe, but an agent cannot determine how the optional parameters affect screening behavior.

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 'Screen' against 'supplied external text' and names the screening criteria: prompt injection, relevance, and substance. This clearly states the tool's function, though it does not explicitly distinguish it from sibling tools such as system_one_review, system_one_verify, or system_one_classify.

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 a use case ('screen supplied external text') but gives no guidance on when to prefer this tool over the many siblings, nor any conditions or exclusions. An agent is left to infer when system_one_screen should be called rather than system_one_review, system_one_gate, or system_one_verify.

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 the security note that it exposes no API credentials, which is useful but doesn't explain what 'bridge capabilities' means or any potential side effects. The description 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?

A single sentence that is direct and to the point, with no unnecessary words. The action and key details are 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 is the only source for return information. It says 'report bridge capabilities' but does not specify the structure or content of the report. For a status tool this may be sufficient, but more explicit details about what capabilities are reported 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?

The tool has zero parameters, so the description does not need to explain parameter semantics. The schema coverage is 100% (empty schema), and the baseline for zero parameters is 4. The description adds no parameter-related information but is not required to.

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: check the configured /v1/models endpoint and report bridge capabilities. This is a specific verb+resource combination that distinguishes it from sibling tools by naming the endpoint and 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?

The description implies use for checking system status but does not explicitly state when to use it vs alternatives or provide exclusions. Given the many sibling tools, explicit guidance would be helpful, but the name and description make the use case fairly obvious.

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 non-destructive behavior. The description adds valuable behavioral context: outputs are probability-based advisory verdicts, not proof, which informs how an agent should interpret results. No contradiction with the annotations exists.

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 one tight sentence with no filler. It front-loads the core operation and follows with the essential advisory caveat, so every phrase 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 no output schema, 0% schema description coverage, and three parameters, the description is not complete enough. It fails to describe what a verdict actually looks like, how confidence is expressed, and how auto_accept affects behavior, leaving an agent to guess at call semantics.

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 0%, so the description must compensate for missing parameter documentation. It clarifies that claims are checked against evidence, but it does not explain the auto_accept threshold, the accepted evidence formats, or constraints on claims. This leaves a key parameter semantically unexplained.

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 and resource: 'Verify claims against supplied evidence,' and adds the clarifying caveat that verdicts are 'probability-based advisory' rather than proof. This distinguishes it from sibling tools like classify or decide by making clear it judges claims against provided evidence rather than producing categorical outcomes.

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 when to use the tool: when a caller has discrete claims and supplied evidence to check. However, it does not explicitly state when to use this over siblings such as system_one_review, system_one_compare, or system_one_decide, and it gives no exclusions or alternative conditions.

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