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

With no annotations, the description fully carries the burden of behavioral disclosure. It accurately describes the absence of outputSchema, the presence of structuredContent, and the empty content array, which is the core behavior being tested. This is precise and useful for an agent.

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 key fact (no outputSchema declared) and immediately explains the test's intent. Every word earns its place; there is no waste or 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 simplicity (zero params, no schema), the description fully explains the scenario and the expected client behavior. The sibling list provides additional context that this is one of several test scenarios, and the description is complete for its purpose.

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 schema provides complete information. The description does not add parameter details, but none are needed. This matches the baseline for no-parameter tools, and the lack of additional info is not a 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's purpose: to test whether a client will surface structuredContent when no outputSchema is declared, given an empty content array. It is specific to the tool's role in a test suite, though it does not explicitly distinguish itself from sibling tools by name.

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 as part of a set of scenario tests for structuredContent handling, but it does not explicitly state when to use this tool versus its siblings. The purpose is clear from context, but no direct alternatives or exclusions are mentioned.

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 available, the description carries the burden, and it discloses key behavioral traits: the lack of an output schema, the dual nature of the result (text + structured), and the fact that values match. It also reveals the testing intent, which is a useful behavioral insight beyond what schema/annotations provide.

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 that is direct and information-dense. It front-loads the most critical fact (no outputSchema) and clearly conveys the tool's purpose 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?

For a simple tool with no parameters and no output schema, the description adequately covers the essential behaviors: the presence of both text and structured content, the matching values, and the opportunistic usage test. It does not describe the actual content values, but that is not necessary given the tool's purpose.

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 baseline is 4. The description appropriately does not need to explain parameter semantics, and the empty schema confirms no parameters exist.

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 purpose: it tests whether structuredContent is used opportunistically when no output schema is declared. It also specifies the distinct behavior of returning both a text block and structuredContent, distinguishing it from siblings like no_schema__text_only and no_schema__structured_only.

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?

Usage is implied rather than explicit. The description explains what the tool does, but does not directly state when to choose this tool over its siblings or provide exclusion criteria. The sibling names suggest a test matrix, but no explicit guidance is given.

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 provided, the description carries the full burden. It clearly discloses that output is plain text only and confirms the absence of an output schema. This gives the agent essential information about the tool's behavior, though it does not elaborate on side effects or error handling.

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 core behavior. 'No outputSchema' and 'Returns a plain text content block only' are direct. The baseline context sentence adds useful historical information without redundancy. Extremely concise 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?

For a tool with no parameters, no annotations, and no output schema, the description is complete. It specifies the return type and the absence of schema, covering all relevant behavioral details. The simple nature of the tool means nothing else is required.

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 is empty. The description does not need to add parameter meaning since none exist. Per the baseline rule for 0 params, a score of 4 is appropriate; the description does not detract from this.

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: 'Returns a plain text content block only.' It explicitly notes 'No outputSchema,' which distinguishes it from sibling tools that include structured output. The behavior 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 lacks explicit guidance on when to use this tool versus alternatives. It only mentions 'This is the pre-2025-06-18 baseline,' which is historical context but does not explain USE cases or exclusions. No alternatives or preferred scenarios are indicated.

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?

No annotations are provided, so the description carries full burden. It explicitly discloses the non-compliant behavior: structuredContent is omitted despite the output schema declaration. This is exactly what an agent needs to know.

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, dense sentence conveys the purpose, the behavioral anomaly, and the testing intent. No wasted words; 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 the simplicity (no params, no nested schema), the description is fully complete. It explains the scenario, the server's non-compliance, and the expected client behavior test.

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 description adds no parameter information. The baseline for 0 params is 4, and there is no deficit to compensate for.

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 a specific behavior: the tool declares an output schema but returns only text content without structuredContent. This is a well-defined test scenario that distinguishes it from sibling tools, which cover other schema/structuredContent permutations.

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 this tool: to test client behavior when a promised schema is never fulfilled. While it does not explicitly name alternatives, the sibling tool names indicate related scenarios, and the intent is unambiguous.

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

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

With no annotations, the description carries the full burden. It explicitly discloses that the content array is empty, there is no text fallback, and the return type is structuredContent. It also notes that an outputSchema is declared. This goes beyond minimal disclosure by specifying exact return behavior, though it does not mention edge cases or error 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 two sentences long, front-loaded with the key behavioral detail (empty content array, no text fallback) and the testing purpose. Every sentence earns its place; there is no waste or 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?

The tool has no parameters and an output schema, so the description does not need to detail return values (schema handles that). It covers the purpose, the specific structuredContent behavior, and the testing context. It is complete for a simple test tool, though it could mention expected usage as a client/model capability check more explicitly.

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?

There are zero parameters, so the baseline is 4. The description does not need to add parameter information because the input schema is empty and coverage is 100%. No additional parameter semantics are required or missing.

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 what the tool does: it returns structuredContent with an EMPTY content array and no text fallback. This is a specific verb ('Returns') plus a resource ('structuredContent') and a distinguishing characteristic (no text fallback), effectively separating it from siblings like text_and_structured variants.

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 usage context: 'Tests whether the client/model can operate on structuredContent alone.' This implies when to use the tool (for testing structuredContent-only handling). However, it does not explicitly mention alternatives or when not to use it, 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?

With no annotations provided, the description carries full behavioral disclosure. It explicitly discloses that the tool returns structuredContent with wrong types and a missing required field, and that its purpose is to test client validation. This is complete transparency for a deliberately faulty test tool.

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, focused sentence that front-loads the key behavior (violates schema) and its testing purpose. No unnecessary 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 zero-parameter test tool, the description adequately explains its purpose and expected behavior. It does not detail the exact output schema structure, but that is irrelevant to the tool's intent. The sister-tool naming adds context, making this description 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?

The tool has zero parameters, so schema coverage is complete and the baseline is 4. The description adds no parameter-specific semantics, but none are needed since there are no inputs.

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 specific function: it declares an outputSchema but returns structuredContent that violates it, testing client validation behavior. This distinguishes it from sibling test tools by the specific kind of violation it introduces.

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's intended use as a test case for validation failure, but it does not explicitly contrast it with sibling tools or state when to use it versus alternatives. The purpose is clear enough, but usage guidance is implicit rather than explicit.

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

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

With no annotations, the description carries the burden of disclosure. It discloses that the tool returns both text and structuredContent, and that they are 'matching'. It does not describe side effects, permissions, or error behavior, but for a zero-parameter tool this is adequate.

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, front-loaded with the key behavior, and contains no wasted words. It efficiently conveys the essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no parameters and an output schema is declared, the description sufficiently covers the behavior. It could mention the tool's demonstrative purpose, but the sibling names and context make it clear enough.

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 0 parameters, and the schema is empty, so there is no parameter information to convey. Per the baseline for 0 params, the description need not elaborate, and it does not obstruct understanding.

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 the tool 'Returns matching text + structuredContent', which clearly indicates the output format and behavior. It distinguishes from siblings by specifying 'matching', implying alignment with the spec, unlike 'with_schema__text_and_structured_mismatched'.

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 'the spec's recommended backward-compatible pattern' implies this tool is the preferred choice among alternatives, but it does not explicitly state when to use it or mention exclusions. Usage guidance is implied rather than explicit.

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

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

With no annotations, the description carries the full burden. It discloses the core behavioral trait: text and structuredContent are intentionally set to disagree to probe client behavior. The mention of 'outputSchema declared' also informs the agent that the tool expects a schema to be present. It could add more detail about return values, but the output schema covers that, so this is adequate.

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 clearly communicates the scenario and the test objective. Every phrase is informative: 'outputSchema declared', 'DISAGREE', and 'Tests which one the client actually feeds to the model / shows the user.' No waste, excellent 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?

Given the tool's simplicity (no params) and presence of an output schema, the description is largely complete. It explains the deliberate mismatch and the testing purpose. It could be slightly more explicit about the expected outputs, but the output schema already documents those. The sibling context further clarifies the test suite role.

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 baseline is 4. The description does not need to explain any parameters, and the empty schema confirms no inputs are required. No additional param semantics are needed.

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 purpose: it tests which content source (text vs structuredContent) the client actually uses when they disagree. The verb 'Tests' plus the specific resource ('which one the client actually feeds to the model / shows the user') makes the intent unambiguous. It also distinguishes itself from siblings (e.g., matching variant) by explicitly highlighting the mismatch scenario.

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 by explaining it tests a specific client behavior under disagreement. While it does not name alternatives or explicitly state 'use this instead of...', the context of siblings and the clear purpose provide sufficient usage guidance. No exclusions are given, but the test scenario is well-defined.

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