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

No annotations are present, so the description carries the full burden of disclosure. It confirms persistence but does not clarify whether notes are appended, how they can be retrieved, or any side effects relative to sibling session tools.

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 wasted words. It efficiently communicates the core purpose without padding.

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

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

For a simple one-parameter tool, the description conveys the basic function and persistence. However, with no annotations or output schema, it leaves gaps about side effects and how the note interacts with the rest of the session.

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 for the single 'note' parameter is 100%, so the baseline is 3. The description adds little beyond the schema, mainly framing the note as textual and tied to the session.

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 ('Add a textual note') and the target ('persistent research session'). It is specific enough to distinguish this tool from siblings like save-paper or clear-session.

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 provided on when to use this tool versus alternatives such as save-paper or get-current-session. The persistent-session context is implied but no exclusions or prerequisites 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, the description carries the full burden. It discloses that the tool analyzes, flags claims, and returns reasons and suggested sources. It does not mention side effects or state changes, but the read-only nature is strongly implied by 'analyze' and 'returns,' which is adequate for a non-destructive analysis 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 two sentences, front-loaded with the primary action, and includes return value details without unnecessary fluff. Every word 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 single-parameter tool with no output schema, the description is complete: it explains the input, the processing, and the return format. No additional information is needed to use the tool correctly.

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

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

The schema already provides a full description of the single parameter 'paragraph,' achieving 100% coverage. The tool description adds minimal extra meaning beyond restating that it's a draft paragraph. Thus 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 the tool's function: 'Analyze a draft paragraph' and 'flag claims that are unsupported, overly absolute, or contradicted.' This verb+resource+outcome distinguishes it from sibling tools like summarize-paper or readiness-report, which serve different purposes.

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 use case: when you have a draft paragraph to check against a paper library. It provides clear context but does not explicitly name alternative tools or specify when not to use it, so it stops 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, the description carries the burden of disclosing behavior. It clearly states the destructive nature ('Clear all data') and the scope ('current research session') with 'resetting completely,' which conveys irreversibility. However, it does not specify whether other persisted data (e.g., saved papers) are affected, nor any confirmation requirements, leaving a small gap.

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 front-loads the action and scope, with no extraneous words. It is appropriately terse for a zero-parameter tool.

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 with no parameters and no output schema. The description fully explains the action and its effect, making it complete for the given complexity. It doesn't describe a return value, but that's not essential for a clearing operation.

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 is empty with zero parameters, so there are no parameter details to explain. The baseline for zero parameters is 4; the description adds no parameter semantics but none are needed, as the tool operates without input.

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 'clear' against the resource 'current research session,' and explicitly states 'all data' and 'resetting completely,' making its function unambiguous. It distinguishes itself from sibling tools like get-current-session by indicating a destructive reset rather than a view operation.

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 is for resetting the session when a clean slate is needed, but it provides no explicit guidance on when to use it versus alternatives, nor any warnings about not using it if data preservation is needed. The context signal is clear, but no exclusions are described.

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 that the tool returns a structured JSON comparison matrix, which is a key behavioral outcome, but it does not define what dimensions are compared, how input IDs are validated, or whether any side effects exist. The description is adequate for a simple read-like tool but lacks depth on failure modes or processing details.

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 clear sentence that front-loads the action and scope, with no redundant filler or extraneous details. It efficiently conveys the core functionality and output format.

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 low complexity and full schema coverage, the description is mostly sufficient, but the lack of an output schema means the agent is not informed about the actual fields or structure of the comparison matrix. It states the output type but not its contents, which could be important for downstream selection. Overall, it's a minimal viable description with a clear gap in matrix details.

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 fully documents the single paperIds parameter (arXiv IDs, min 2, max 5), giving 100% coverage. The description only restates the count range, adding no additional semantics beyond what the schema provides. Therefore, 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 clearly identifies the verb 'compare' and resource 'research papers' with an explicit range (2-5), distinguishing it from sibling tools like summarize-paper or check-citations. The output is also specified as a 'structured JSON comparison matrix,' 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?

No explicit when-to-use or alternative guidance is provided, but the phrase 'Compare 2-5 research papers side-by-side' implies the tool is intended for direct multi-paper comparisons. There is no mention of when to prefer this over summarize-paper or check-citations, leaving the agent to infer usage from context.

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 adds a behavioral detail—output renders as a browsable grid—beyond the basic search action. However, without annotations, it doesn't disclose potential API limitations or explicitly state that it's a read-only operation, though search implies this.

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, front-loaded with the verb and resource. Every word contributes value 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 search tool with two parameters and a clear output description, the description is adequately complete. It explains the data source and output format. Minor gaps exist (e.g., no mention of sorting or API rate limits), but the schema covers default limit.

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

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

Schema coverage is 100%, so both parameters (topic, limit) are already well-documented. The description adds no additional semantic detail beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the action (search), resource (arXiv library), and output (matching paper cards rendered as a grid). It distinguishes itself from sibling tools like save-paper or summarize-paper by focusing on discovery.

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 clear context: use this tool when you need to search for papers by topic. It doesn't explicitly mention alternatives or exclusions, but the purpose is straightforward and the sibling tools have different functions.

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 discloses that the tool queries arXiv and produces an analysis of gaps, which is useful. However, it doesn't specify the output format, any network dependency implications, or whether it interacts with session state. For a read-only analysis tool, this is adequate but not rich.

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, well-structured sentence that lists the three types of outputs. It is concise, front-loaded, and every word contributes to the tool's purpose.

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 only one parameter and no output schema, so the description needs to explain the result. It does list what it identifies (under-explored areas, open problems, ideas), but it doesn't state the response format or whether it saves anything. Given the sibling tools (save-paper, clear-session), some session context would be helpful, but the current description is not grossly 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 100% for the single 'topic' parameter, so the schema already documents it fully. The description's phrase 'on a topic' simply echoes the parameter without adding new meaning. Thus the baseline of 3 applies.

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

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

The description clearly states the tool's action ('Analyze the latest arXiv papers'), the target resource (arXiv papers on a topic), and the specific outcomes (under-explored areas, open problems, novel project ideas). It distinguishes itself from siblings like discover-papers by focusing on analysis for gaps rather than just finding papers.

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 you want research gaps on a topic) but gives no explicit when-not-to-use guidance or alternatives. It doesn't contrast with sibling tools like discover-papers or summarize-paper, though the purpose is reasonably 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?

With no annotations, the description carries the full burden. It discloses the behavioral steps (search, summarize, compare) but does not mention output format, external dependencies, or side effects (e.g., session updates). This is only partially transparent.

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

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

The description is a single, focused sentence that front-loads the core action and lists the method succinctly. No redundant details.

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

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

Given the simple parameter and no output schema, the description explains the high-level process and expected outcome (a comprehensive review). However, it lacks details on the review's structure or return format, and does not address potential constraints or interactions with session state, leaving minor 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?

Schema description coverage is 100% with a clear description for 'topic'. The tool description does not add additional parameter semantics beyond what the schema provides, so the baseline of 3 is appropriate.

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

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

The description uses a specific verb ('Generate') and resource ('comprehensive AI literature review') and outlines the process (searching arXiv, summarizing, comparing). This clearly distinguishes it from siblings like 'summarize-paper' or 'compare-papers'.

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 clearly implies the tool is for generating a comprehensive review on a given topic, providing clear context. However, it does not explicitly mention when to prefer this over narrower sibling tools or include exclusions, so it misses the full 'when vs alternatives' 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. 'Retrieve' suggests read-only behavior, and it discloses the side effect of opening the Research Workspace widget. However, it does not explicitly state that it is safe/non-mutating or describe any potential side effects beyond the widget, leaving some ambiguity.

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. The first sentence states the core functionality and enumerates contents; the second sentence adds a relevant behavioral note about opening the widget. It is 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?

Given no output schema, the description provides a good sense of what is returned (topic, papers, reviews, etc.). It also mentions the widget opening, which is useful context. However, it does not specify the structure of the response or behavior when no session exists, leaving minor 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 tool has 0 parameters, and the schema reflects this with no properties. Per guidelines, a parameterless tool earns a baseline of 4. The description adds no parameter-specific semantics but is not required to, as there are none.

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 retrieves the entire persistent research session, with a specific verb ('Retrieve') and resource ('research session'). It lists the contents (topic, papers, reviews, gaps, notes, saved papers), distinguishing it from siblings like clear-session or save-paper, which are clearly different operations.

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 is for getting the current state of the research session, but it does not explicitly state when to use it versus alternatives. No exclusions or alternative tool names are provided, so 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 provided, the description carries the full burden of behavioral transparency. It discloses what the tool checks (entry resolution, topic coverage, missing IDs), implying it will validate IDs against arXiv and analyze their topics. It does not state side effects or error handling, but the read-only nature is implicitly clear. The description adds a reasonable amount of behavioral context beyond the name.

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 efficiently conveys the purpose, input, and output components. It is front-loaded with the main action and avoids waste. Every clause adds value: input specification, output type, and the elements of the summary.

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?

Even without an output schema, the description lists the key components of the summary (resolved entries, topic coverage, missing IDs), giving the agent a clear idea of what to expect. Since the tool has only one parameter and no nested objects, the description is sufficiently complete for context. It could mention the response format (e.g., text vs. structured data), but that is not required for basic 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 for the single parameter 'paperIds' is 100% covered, so baseline 3 applies. The description adds context ('ids that make up a bibliography') but does not provide new semantic detail about the parameter format beyond what the schema already gives (an array of arXiv ID strings). No further compensation is necessary.

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: given a list of arXiv paper IDs, it produces a citation-readiness summary including resolved entries, topic coverage, and missing IDs. The verb 'produce a citation-readiness summary' is specific and the resource is well-defined. It distinguishes itself from siblings like check-citations by adding 'coverage by topic' and 'missing ids'.

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: it is for assessing the readiness of a bibliography from a list of arXiv IDs. However, it does not explicitly mention when to use this tool versus alternatives (e.g., check-citations), nor does it state any exclusions or prerequisites. The context is clear but the guidance is not 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 provided, the description carries the full burden of behavioral disclosure. It indicates a write operation ('save') but does not explain idempotency, duplicate handling, return values, or side effects beyond persistence. This leaves significant behavioral ambiguity.

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 front-loads the verb and key resource, with no unnecessary words or redundancy. It is appropriately 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?

Given the lack of output schema and annotations, the description should explain more about the tool's behavior, such as whether it returns a confirmation or handles duplicate saves. The simple action is stated, but the absence of return value or error behavior makes it incomplete for an agent to fully anticipate the tool's response.

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 already provides complete descriptions for all three parameters (100% coverage), so the baseline is 3. The tool description adds no additional parameter semantics beyond what the schema already states.

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 ('Save'), the object ('a paper'), and the destination ('your persistent research session'). It distinguishes the tool from siblings like add-note or clear-session by specifying the paper-saving 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 phrase 'for later reading or reference' implies the intended use case, but there is no explicit guidance on when to choose this tool over alternatives or any exclusions. Usage is inferred rather than stated directly.

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 burden. It discloses the output type ('structured summary') and the 'single paper' constraint, but does not mention potential side effects, error conditions, or whether it is read-only. This is minimal viable transparency for a simple 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?

Two concise sentences: the first states the tool's purpose, the second gives usage guidance. No wasted words, and key information is front-loaded.

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

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

Despite low complexity and full schema coverage, there is no output schema and the description only vaguely references 'structured summary' without specifying the summary's format or fields. This lack of return-value detail leaves a gap for the 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 coverage is 100%, so the baseline is 3. The description adds value by instructing the agent to use the id returned by discover-papers, providing integration context beyond the schema's simple format example.

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 summarizes a single paper via its arXiv id and produces a structured summary. The verb 'summarize' and resource 'single paper by its arXiv id' are specific, and the mention of discover-papers distinguishes it from sibling tools like compare-papers and generate-literature-review.

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 clear context on when to use the tool: after getting an id from discover-papers. It implies a workflow (discover first, then summarize) but does not explicitly state when not to use it or mention alternatives, so it lacks full exclusion guidance.

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