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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions the handle is 'short-lived' and 'explicit,' but does not explain what the handle is for, what it returns, any side effects, or lifecycle details. For a creation tool, this is insufficient.

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 action, and contains no unnecessary words. It is appropriately 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?

The tool is simple (1 parameter) and has an output schema, so the description does not need to explain return values. However, it lacks context about how the handle is used, its lifecycle, and its relationship to sibling tools like use_handle. This incomplete context could confuse agents.

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 input schema has 100% description coverage for the 'target' parameter, so the baseline is 3. The tool description adds no additional parameter-level context beyond restating the purpose.

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 verb 'creates' and the resource 'explicit short-lived probe handle,' and it adds the specific purpose 'to test stateless multi-call tool design.' This distinguishes it from sibling tools like use_handle, which presumably consumes the handle.

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 for testing stateless multi-call tool design but does not explicitly state when to use this tool versus alternatives like use_handle. No exclusions or when-not-to-use guidance 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?

With no annotations provided, the description carries the full burden. It transparently states that the tool returns the received arguments and MCP metadata, and specifically calls out the metadata fields. This is a read-only behavior implied by 'Returns,' and it discloses what the agent can expect without needing to infer hidden side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exactly two sentences. The first sentence states the core function, and the second provides usage guidance. Every word earns its place, with no filler or repetition. It is front-loaded with the primary purpose and immediately actionable.

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?

This is a simple tool with one optional parameter and an output schema present. The description fully covers its purpose and usage context. Since the output schema exists, the description does not need to explain return values. For the tool's complexity, the description is complete and well-rounded.

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 input schema fully documents the only parameter 'message' with a description ('Any message to echo back'), so schema coverage is 100%. The description does not add any additional parameter-specific meaning beyond what the schema provides, but it does mention 'received arguments' which encompasses the parameter. This meets the baseline of 3.

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 'Returns the received arguments and MCP request metadata,' which is a specific verb+resource combination. It distinguishes itself from siblings by explicitly mentioning metadata fields (protocolVersion, clientInfo, clientCapabilities) and the directive to 'Use this first,' making its diagnostic role clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit usage context: 'Use this first to inspect protocolVersion, clientInfo, and clientCapabilities.' This tells the agent when to invoke the tool, though it does not explicitly name alternatives or exclusions. The clear 'use this first' directive provides adequate 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?

Beyond the readOnlyHint annotation, the description adds that this is a 'ChatGPT-compatible' and a 'stub,' suggesting a simulated or compatibility-oriented behavior, and that it returns 'full text' for the ID. This provides useful context not present in annotations, with no contradictions.

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 short sentences with no filler. The first provides contextual framing ('stub'), the second the core functionality. Every word contributes meaning.

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 fetch operation with an output schema and clear read-only annotation, the description sufficiently covers purpose, input requirement, and relationship to search. The 'stub' characterization adds a behavioral hint without needing further detail.

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 already provides 100% parameter coverage with 'Document ID returned by search.' The tool description echoes the same requirement without adding new semantic details, so it stays at the baseline for high schema coverage.

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 'Retrieves full text for an ID returned by search,' specifying the verb (retrieves), resource (full text), and the relationship to the search tool. This distinguishes it from siblings like search (which finds IDs) and handle tools.

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 ties usage to search by requiring an ID returned by search, implying the correct invocation sequence. It does not explicitly name alternatives or exclusion conditions, so it doesn't reach 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, the description carries the full burden. It discloses the key behavioral trait: the tool repeatedly returns input_required until the client sends inputResponses. However, it doesn't specify what happens after the retry or any side effects, but for a simple test 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?

Two sentences, front-loaded with the return behavior and testing purpose. 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 simple tool with one parameter and no output schema, the description covers the core behavior and purpose. It might benefit from stating the expected response after inputResponses, but the description is sufficient for an agent to understand invocation context.

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% with a clear description of 'topic'. The main description doesn't add significant new meaning beyond the schema; it reinforces the context of follow-up input but doesn't explain format or constraints. Baseline 3 applies given high schema coverage.

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 behavior: it returns resultType input_required until retried with inputResponses. It also states its testing purpose (MRTR and elicitation form mode), clearly distinguishing it from siblings like echo_meta or structured_result.

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 identifies a clear use case: testing MRTR and elicitation form mode. It doesn't explicitly mention when not to use it or alternatives, but the testing context is specific enough for an agent to select it appropriately.

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 the full burden. It only states the return type and points at a probe resource, but gives no information about side effects, error behavior, permissions, or whether the operation is read-only. This is minimal transparency.

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. It is appropriately concise and front-loaded, stating the core behavior immediately.

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 and no annotations, the description is too sparse. It does not explain what a resource_link content item is, what a probe resource is, or how to handle the result. This leaves significant gaps for an agent selecting among sibling tools.

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 has no need to explain parameter syntax or semantics. The baseline for zero parameters is 4, and the description does not miss anything here.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns a resource_link content item, which is specific and differentiates it somewhat from generic tools. However, it does not clarify what a 'probe resource' is or how this differs from sibling result tools like structured_result or echo_meta.

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 alternatives. The description lacks any mention of prerequisites, exclusions, or sibling tools, leaving the agent without a basis for 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?

The readOnlyHint annotation already covers safety, and the description adds context by stating it is a 'stub' and returns specific fields (IDs, titles, URLs). This provides behavioral insight beyond the annotation, though it does not elaborate on limitations like pagination or result counts.

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 that states purpose, output, and usage guidance without any redundancy. It is front-loaded and immediately clear.

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 simple one-parameter search tool, the description covers its return values and relationship to fetch. The presence of an output schema and annotations reduces the burden, and the description fills the essential gaps.

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 has 100% coverage for the single 'query' parameter with a basic description. The tool description does not add any additional semantics beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool performs a search, returns result IDs, titles, and URLs, and is specifically for probe documents. It distinguishes from the sibling tool 'fetch' which retrieves full text, making the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'Use fetch to retrieve full text,' providing a clear alternative and when to use another tool. It also labels the tool as read-only, suggesting it is for search queries only, not for retrieval or modification.

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 must carry the full burden of disclosing behavior. It does state the core return behavior (both text and structuredContent), which is useful, but it does not address the role of the label parameter, edge cases, or any limitations. This is minimal but not misleading.

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 sentence that front-loads the primary action and includes no filler or redundant information. Every word contributes to understanding the tool's function, making it highly 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?

The tool is simple: one optional parameter, no required fields, and an output schema. The description states the core return behavior, and the output schema presumably covers the structure of structuredContent. However, it does not mention the intended use case or how the label parameter influences the result, leaving a small but noticeable gap. Given the simplicity, it is mostly 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 input schema has 100% coverage for the single optional 'label' parameter, described as 'Optional label for the generated result.' The description adds no further semantic detail about how the label affects the output, so it remains at the baseline for high schema coverage without adding extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool's primary function: returning both text content and structuredContent conforming to outputSchema. This clearly identifies what the tool does, though it does not explicitly differentiate it from sibling tools like resource_link_result. The verb 'Returns' and the specific resource make the purpose clear.

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 alternatives. The description only states what it does, without mentioning any context, prerequisites, or exclusions. Sibling tools are listed but not referenced, so the description fails to help the agent decide when to invoke this tool.

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 disclosure responsibility. It clearly states the tool always errors with isError true and clarifies that it is not a protocol-level error, providing useful context. It does not detail the error message content, but the key behavioral trait is fully disclosed.

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 the core behavior front-loaded ('Always returns a tool execution error'). It is concise and contains no unnecessary words or filler.

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, no-output-schema tool, the description is fully complete. It precisely specifies what the tool does without needing to explain parameters or return values. The purpose is fully captured.

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 empty schema is fully covered. The description adds no parameter semantics because none are needed. The baseline for 0 params is 4.

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 always returns a tool execution error via isError true, and explicitly distinguishes this from a JSON-RPC protocol error. This specific verb and resource make the tool's purpose unambiguous and differentiate it from siblings like structured_result or echo_meta.

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 only states what the tool does, not when or why to use it. It does not reference any testing scenarios or contrast with alternative tools. There is no when-to-use or when-not-to-use 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?

With no annotations, the description carries the full burden. It discloses one behavioral trait: unknown handles return a tool execution error. But it does not describe success behavior, side effects, or whether the operation is read-only or mutating. This is minimal transparency beyond the error condition.

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, compact sentence that states the essential dependency on create_handle and the error behavior for unknown handles. It is appropriately sized and front-loaded, with 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?

Despite having an output schema and two well-documented parameters, the description fails to convey the tool's actual operation or purpose. It does not explain what 'uses a handle' accomplishes, making the tool's functionality incomplete for an agent trying to select and invoke it correctly. The error condition is noted, but the success path and overall behavior are absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description reinforces the handle parameter's origin ('returned by create_handle') but adds no additional meaning to 'query' beyond the schema's 'Probe query.' It does not compensate for or enhance the parameter understanding beyond what the schema already provides.

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 'Uses a handle returned by create_handle,' which identifies the tool as the counterpart to create_handle and distinguishes it by its dependency on a prior handle. However, the verb 'uses' is vague—it does not specify what action is performed with the handle or what output is produced, leaving the core purpose unclear.

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 that the tool should be used after create_handle, since it requires a handle returned by that tool. It also warns that unknown handles error, which guides the user to provide a valid handle. However, it does not state when to use this tool instead of other siblings (e.g., search, fetch) or specify exclusions.

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