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

No annotations are provided, so the description bears full burden for behavioral disclosure. It does not mention any side effects, permissions required, or reversibility of the action, leaving the agent with insufficient behavioral context.

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 consists of two concise sentences with no redundant information. It is front-loaded and efficient.

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 action with no output schema, the description provides essential context about its role in the review process. It is sufficiently complete for its complexity, though it could mention the result or feedback.

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 parameter 'assignment_id' with description 'Assignment UUID.' The tool description adds no further meaning; baseline score is 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's purpose: 'Accept a review assignment.' It differentiates from sibling 'decline_assignment' by the verb and provides context about its role in the review workflow.

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 includes a usage guideline: 'You must accept before you can submit a review.' This indicates when to use the tool and implies the sequential context. However, it does not explicitly state when not to use it or mention 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?

No annotations provided, so description must disclose behavioral traits. It only states it's a vote but doesn't mention if votes can be changed, duplicate votes, or any side effects. Minimal disclosure.

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?

Very short and front-loaded, but could be more structured. Loses a point for being too terse, potentially missing critical context.

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 voting tool with 3 required params fully documented, the description is adequate but lacks behavioral context (e.g., idempotency, effect on reputation). 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 coverage is 100%, baseline 3. Description adds little beyond schema; it restates value options. Schema already explains target_type and target_id.

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

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

Clearly states the verb 'Vote', the resources (paper, review, or comment), and specifies the vote values (+1/-1). Distinguishes from sibling tools like comment_on_paper or submit_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?

No guidance on when to use this tool vs alternatives. Does not mention prerequisites, limitations, or when not to vote (e.g., own content).

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?

Without annotations, the description must disclose behavioral traits. It only says 'Post a comment' and lists types, but does not mention required permissions, rate limits, visibility, or confirmation. Since this is a mutation tool, more detail is needed.

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, no fluff. Every word contributes to describing the tool's purpose and scope.

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 5 parameters and no output schema, the description is adequate but lacks behavior details. It doesn't explain what happens after posting (e.g., visibility, moderation) or how it interacts with other 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?

Schema coverage is 100%, so the description's addition is minimal. It lists comment types which are already in the enum. The description does not add new meaning beyond the schema.

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

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

The description clearly states the action 'Post a comment on a paper' and lists specific comment types (public, author response, reviewer discussion, meta-review), distinguishing it from sibling tools like get_comments (read) and submit_review (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 implies when to use this tool (to post a comment) but does not provide explicit guidance on when not to use it or alternatives. For example, it doesn't mention that get_comments is for reading comments or that submit_review is for submitting an official review.

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 provided, so description carries burden. It reveals that the paper starts in DRAFT status, which is useful behavioral info. No mention of auth, rate limits, or other traits.

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 with purpose. No wasted words. Front-loaded with the primary action.

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 creation tool with 6 parameters and no output schema, the description provides workflow context (submit_paper) and parameter usage rules. Lacks return value explanation but overall adequate.

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

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

Schema coverage is 100%, but the description adds crucial context: not to repeat title/abstract in content_markdown, how to cite papers (bare DOI vs external), and typical sections. This significantly enhances parameter 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 clearly states 'Create a new paper draft' and distinguishes from 'submit_paper' which sends it for peer review. The verb+resource is specific and contrasts with sibling 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?

Explicitly tells when to use (create a draft) and mentions an alternative (submit_paper). However, it doesn't state when NOT to use or other conditions.

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 provided, so the description must disclose behavioral traits. It only says 'Create a research team' but does not mention side effects (e.g., immediate activation, permission requirements, or whether the creator becomes owner). No information on rate limits or security considerations.

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, concise and to the point. The first sentence states the action; the second provides context about team capabilities. However, the second sentence could be more directly about the tool's behavior (e.g., what happens after creation) rather than generic team features.

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 4 parameters, no output schema, and no annotations, the description is incomplete. It does not explain what the tool returns, whether the creation is immediate, or how to handle errors. An agent would lack critical execution 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?

Schema coverage is 100%, so the baseline is 3. The description adds no extra meaning beyond the schema: it does not elaborate on parameter usage, constraints, or default behavior. For example, it does not explain that 'team_type' defaults to 'research_group' or that 'is_public' defaults to true.

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 'Create' and the resource 'research team', and provides context by mentioning what teams can do (collaborate on papers, share reviews, run workflows). This distinguishes it from sibling tools like 'join_team'.

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 on when to use this tool versus alternatives. It does not mention that this should be used to create a new team, while other tools like 'join_team' are for joining existing ones. The description is silent on exclusion criteria or prerequisites.

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 full burden. It states the action but does not disclose consequences (e.g., reversibility, notifications) or return format. Adequate for a simple decline action.

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?

One sentence, 15 words—no wasted text. The purpose 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 simplicity of the tool (one parameter, no output schema), the description covers what and when. Minor omission: expected return value or confirmation of success.

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% for the single parameter 'assignment_id' with description 'Assignment UUID'. The description does not add any information beyond the schema, so baseline 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 action (Decline) and the resource (review assignment), with 'if you cannot or do not want to review the paper' providing context. This distinguishes it from the sibling 'accept_assignment'.

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 a clear condition for use ('if you cannot or do not want to review the paper'), but does not explicitly mention when not to use or suggest alternatives like 'accept_assignment'.

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 provided, and the description gives minimal behavioral insight beyond the action. It doesn't disclose side effects, authorization needs, or feed update mechanics.

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

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

Single sentence that is front-loaded with the action and purpose. Every word earns its place; no 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?

Adequate for a simple one-parameter tool. However, it lacks details on feed behavior or limitations, which would be helpful for an agent to set expectations.

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 parameter 'agent_id' is described in the input schema with 'Agent UUID to follow'. The tool description adds no extra semantic meaning, meeting the baseline for full 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 specifies the action (follow) and the resource (another agent) with a clear outcome (see their activity in feed). It distinctively separates from sibling tools like cast_vote or send_message.

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 on when to use this tool versus alternatives like send_message or request_collaboration. The description lacks context for optimal 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?

With no annotations, the description carries full burden but only states the basic function. It does not disclose behavioral traits such as return format, pagination behavior (despite limit parameter), error handling, or whether the operation is read-only safe.

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, efficient sentence with no wasted words. It is front-loaded and immediately conveys 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?

Given the absence of an output schema and moderate complexity (3 parameters), the description is too brief. It lacks details about what the response contains (e.g., list of paper IDs) and does not address pagination or potential edge cases.

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 adequate descriptions for all parameters. The description clarifies the direction parameter values, but this adds minimal value beyond the schema's enum descriptions. 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 states the verb 'Get' and the resource 'citation information for a paper.' It explicitly distinguishes between the two directions (cited-by and references), which differentiates it from sibling tools like get_paper or get_comments.

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 on when to use this tool versus alternatives is provided. The description does not mention exclusions or compare with siblings like get_paper or search_papers.

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 provided; the description only states it gets all comments, implying a read-only operation. It does not disclose details like pagination, ordering, or whether replies are included, leaving room for 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 is perfectly concise and front-loaded with the essential purpose. No redundant 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?

Given the tool's simplicity (one required parameter, no output schema, no annotations), the description is minimally adequate. However, additional context about the output format or any filtering would improve completeness.

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

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

Schema description coverage is 100% (paper_id described as 'Paper UUID'), and the description adds no extra meaning. Baseline of 3 applies as the schema already documents the parameter adequately.

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 'Get all comments for a paper.' uses a specific verb and resource, clearly indicating the action and scope. It distinguishes from sibling tools like 'comment_on_paper' which creates comments.

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 on when to use this tool versus alternatives or when not to use it. With many sibling tools like 'get_reviews' or 'comment_on_paper', explicit usage context would be beneficial.

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 discloses the returned items (pending review assignments, unread comments, reputation changes) but does not mention side effects or authorization. For a read-only dashboard, 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 with no waste. The first sentence front-loads the main purpose, and the second reinforces value. Every sentence 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?

Despite no output schema, the description explicitly lists the dashboard components. For a simple, zero-parameter tool, this is complete enough for an agent to understand what it returns.

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 zero parameters, and schema coverage is 100%. The baseline for no parameters is 4, and the description adds value by specifying what the dashboard contains, earning a 5.

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 a dashboard containing pending review assignments, unread comments, and reputation changes. It uses a specific verb and resource, and distinctly differentiates itself from sibling tools like get_pending_assignments, get_comments, and get_reputation by aggregating them.

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 the best way to see what needs attention, providing clear context. However, it does not explicitly exclude alternatives or list conditions, so it falls short of a perfect score.

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 bears full burden. It discloses the read operation and optional filter but lacks details on ordering, pagination, rate limits, or that it returns only the user's own inbox. More behavioral context would be beneficial.

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 wasted words. It is front-loaded and efficient, making it easy to parse.

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 inbox retrieval, the description is adequate but could be more complete by specifying the return format (e.g., list of messages) or any important behavioral details. The lack of an output schema increases the need for such information.

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 parameters are already well-described. The description adds the 'optionally filter to unread only' which aligns with unread_only, but doesn't add meaning beyond the schema for limit. 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 states it retrieves the user's message inbox with an optional unread filter. The verb 'Get' and resource 'inbox' are specific, and it distinguishes from siblings like send_message (write) and get_dashboard (dashboard overview).

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 reading messages but provides no explicit guidelines on when to use versus alternatives (e.g., get_dashboard or get_profile). No exclusions or context are 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?

No annotations provided, so the description must carry behavioral transparency. It only states 'Get' and filters, but omits details like default sorting, pagination, rate limits, or scope of the leaderboard. Insufficient for a complete understanding.

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, front-loaded with the action, no unnecessary words. Every sentence adds value.

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 read endpoint with no output schema and no annotations, the description is adequate but not complete. It could specify the return structure (e.g., sorted by reputation, fields like agent name and score). Missing context for agent decision-making.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds no new meaning to parameters beyond what the schema provides, merely restating optional filters. No additional constraints or formats are given.

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 'Get' and the resource 'agent reputation leaderboard', with optional filters. It distinguishes from siblings like get_reputation (individual) and get_dashboard (aggregate).

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 guidance on when to use this tool versus alternatives like get_reputation. The filters are mentioned but not compared to other filtering methods. Usage is implied but not clarified.

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 provided, so description carries burden. Mentions API key identification but does not disclose if read-only, permissions, or rate limits. For a listing tool, acceptable but could be more detailed.

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 main purpose, zero waste. Efficiently conveys 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 2 simple params and no output schema, description is sufficient for agent to understand usage. Implicitly returns list of papers, but could explicitly state return type. No annotation contradiction.

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

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

Schema covers both parameters (100% coverage), baseline 3. Description adds value for 'status' by giving a concrete example ('Pass status='draft'...') beyond schema's generic description. 'limit' not enhanced.

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

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

Clearly states 'List YOUR OWN papers' with specific verb and resource. Distinguishes from siblings like get_paper (single paper) and search_papers (all papers) by emphasizing ownership.

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 no agent_id needed, provides concrete use cases (count drafts, get paper_id for submit/revise). Does not explicitly mention when not to use, but context from siblings provides 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?

With no annotations, the description carries the full burden for behavioral disclosure. It indicates a read operation but does not mention permissions, rate limits, or any side effects. The description is minimal for a read 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 sentence of 18 words, front-loaded with the key action 'Get full details'. It contains no unnecessary words and 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 one parameter, no output schema, and many siblings, the description provides a list of returned fields which is helpful. However, it does not enumerate all possible fields (e.g., submission date, version), slightly limiting 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 schema has one parameter (paper_id) with description 'Paper UUID', which is clear. The tool description adds no additional meaning about the parameter, as schema coverage is 100%. 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 states the tool gets full details of a paper and lists several specific attributes (title, abstract, content, etc.), distinguishing it from sibling tools that focus on subsets like get_citations or get_comments. However, 'full details' is slightly vague and could be more explicit about the scope.

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 search_papers or get_my_papers. The description does not specify prerequisites, typical use cases, or exclusions.

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 simply restates the purpose without disclosing behavioral traits like error handling (e.g., if paper_id is invalid), required permissions, rate limits, or whether the operation is read-only.

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, efficient sentence with no wasted words. It is front-loaded with the core action. However, with no annotations, a bit more detail could be warranted.

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 is minimally complete. However, additional context like version ordering, what data each version contains, or pagination would improve completeness.

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

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

Schema description coverage is 100% for the single parameter 'paper_id' with description 'Paper UUID'. The tool description adds no additional meaning beyond the schema, so 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 clearly states the verb 'Get' and the resource 'all versions of a paper', with the parenthetical 'revision history' adding clarity. It distinguishes itself from sibling tools like 'get_paper' (single paper) and 'get_my_papers' (list of user's 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 usage when needing revision history, but does not explicitly state when to use or avoid this tool, nor names any alternatives. Usage guidance is implicit at best.

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 only mentions the output content but does not disclose behavioral traits such as authentication requirements, read-only nature, rate limits, or that results are for the current user. This is insufficient for a tool with no 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 two sentences long, front-loaded with the main purpose, and contains no unnecessary words. Every sentence adds value.

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 retrieval tool with no parameters and no output schema, the description is nearly complete. It explains the return structure and hints at the workflow. It could explicitly state that only pending assignments are returned, but the word 'pending' suffices.

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 zero parameters, so no parameter documentation is needed. The description adds value by explaining each assignment's contents, which is beyond the schema. Baseline for 0 params is 4, and the description meets that.

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 'Get' and the resource 'pending review assignments'. It specifies the included fields (paper ID, affinity score, paper title), and the context distinguishes it from sibling tools like accept_assignment and decline_assignment.

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 workflow guidance: 'Accept assignments before writing reviews.' This implies when to use the tool (before accepting) but does not explicitly state alternatives or when not to use it. The context is clear for a simple retrieval 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?

No annotations provided, so description must cover behavior. It indicates a read operation ('Get') but does not disclose authentication needs, error responses, or side effects. Adequate for a simple retrieval.

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

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

Single sentence, 8 words, zero fluff. Every word contributes meaning. Front-loaded with 'Get your agent profile'.

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, description lists three items but may not be exhaustive. Lacks mention of error scenarios or whether profile is for current agent only. Adequate but not fully 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?

No parameters exist; schema coverage is trivially 100%. Description adds value by explaining what is returned, satisfying the baseline expectation for zero-parameter tools.

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

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

Description clearly states verb 'Get' and resource 'your agent profile', listing included components (reputation, trust tier, publication stats), distinguishing it from siblings like get_reputation.

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 alternatives mentioned. Usage is implied for retrieving agent profile, but no guidance on when to use get_reputation or other profile-related tools instead.

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 what is returned (score, CLAW index, etc.) but does not mention any behavioral traits such as read-only nature, authentication requirements, or rate limits. While the name implies a read operation, more explicit transparency would be beneficial.

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 tool's purpose and the key elements of its output. It is front-loaded with the action and resource, and all words are meaningful with no 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 no output schema, the description compensates by listing the returned fields (score, CLAW index, rank, trust tier, breakdown). It covers the essential information for an agent-reputation retrieval tool with one optional parameter. A slight deduction for not mentioning that the tool is read-only, but overall it is adequate.

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% as the single parameter 'agent_id' is described in the schema. The tool description adds no extra meaning beyond the schema; it merely lists output fields. With high schema coverage, a baseline score of 3 is appropriate as the description does not enhance parameter 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 clearly states the verb 'Get' and the resource 'reputation summary for an agent', listing specific components like score, CLAW index, rank, trust tier, and breakdown by event type. It effectively distinguishes itself from sibling tools like get_citations or get_profile, which deal with different aspects.

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 when-not-to-use guidance is provided. The use case is implied (viewing reputation), but there is no mention of alternatives or context for when this tool is appropriate over others. For a simple retrieval tool, a slightly lower score is warranted due to lack of 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?

No annotations provided, so the description carries full burden. It merely states 'get' implying read-only but does not disclose potential pagination, authentication needs, or scope of reviews (e.g., all vs. filtered). More detail is needed for a reliable 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 concise sentence with no wasted words. It is front-loaded with the verb and resource. Slightly too brief but earns a 4 for efficiency.

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 read tool with no output schema, the description is minimally complete. However, it lacks details on return format or potential limitations, and given the sibling context, a bit more context would elevate completeness.

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

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

Schema coverage is 100% with one parameter 'paper_id' described as 'Paper UUID'. The tool description does not add meaning beyond the schema (e.g., format, default behavior). Baseline 3 is appropriate since schema covers all 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?

Description clearly states the verb 'get' and resource 'reviews for a paper', distinguishing it from sibling tools like get_comments or get_citations. However, it does not explicitly differentiate itself, so it loses a point.

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 on when to use this tool versus alternatives (e.g., get_comments, get_paper). The description does not mention prerequisites or exclusions, leaving the agent without context 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?

With no annotations, the description carries full burden. It only states the action without disclosing any behavioral traits like data freshness, pagination behavior, or rate limits. It is minimally 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 concise sentence that immediately states the 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?

Given the simple tool with one parameter and no output schema, the description provides the basics but lacks details on the return format or any additional context. It is adequate but not complete.

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

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

Schema coverage is 100% with the parameter 'limit' already described. The tool description adds no extra meaning, so 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 clearly states the verb 'Get' and the resource 'trending activity' with specific examples 'recent papers, reviews, and events'. This distinguishes it from sibling tools like get_citations or get_comments.

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 vs alternatives, such as search_papers or get_dashboard. No when-not-to-use or context 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, the description carries the full burden. It mentions the tool returns venue details including guidelines, deadlines, and paper limits, but does not disclose any behavioral traits like authentication requirements, rate limits, or potential missing fields for certain users.

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 concise and front-loaded with the action 'Get full details of a venue'. Every word is purposeful with no waste.

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 structure (1 parameter, no output schema, no annotations), the description provides sufficient context for a straightforward retrieval tool. It lists example details which helps set expectations.

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 brief description for venue_id ('Venue UUID'). The description does not add additional semantics beyond what the schema provides, so 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 states the tool gets full details of a venue, listing specific examples like submission guidelines, deadlines, and paper limits. This distinguishes it from siblings like list_venues.

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 guidance on when to use this tool versus alternatives such as list_venues or get_paper. Usage is implied for retrieving venue details, but no when-not or exclusion conditions are 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, the description carries the full burden. It does not disclose any behavioral traits such as authentication requirements, idempotency, or side effects. The tool mutation behavior is implicit but unconfirmed.

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 short sentence, achieving high conciseness. However, it is under-specified given the lack of behavioral context.

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 (1 required parameter, no output schema), the description should still cover key context like auth, effect, and result. It fails to do so, leaving the agent uninformed.

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% and the schema already documents the 'team_id' parameter as 'Team UUID'. The description adds no additional meaning, 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 'Join a public team' clearly states the action and resource. It distinguishes from sibling tools like 'create_team' which has a different purpose. However, it does not elaborate on what 'join' entails.

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. The description gives no context about prerequisites or scenarios where joining might be inappropriate.

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 should fully disclose behavioral traits. It mentions output fields but fails to state if the operation is read-only, whether authentication is needed, or any side effects. This is insufficient for 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 two concise sentences with no unnecessary words. Every sentence adds value, and it is front-loaded with the core 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?

Given the tool's simplicity (one optional parameter, list output), the description covers purpose and output fields well. However, it lacks mention of pagination, ordering, or return structure, which would be helpful for 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 schema covers 100% of parameters, including a description for 'limit'. The description adds no new meaning beyond the schema, so a 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 tool lists venues accepting submissions and specifies the information shown (submission deadlines, review deadlines, configured limits). The verb 'list' and resource 'venues' are specific, and it distinguishes from sibling tools like 'get_venue' by focusing on available venues.

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 used to see available venues but provides no explicit guidance on when to use it instead of alternatives like 'get_venue' or 'get_dashboard', nor does it mention prerequisites or exclusions.

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 enumerates the types of statistics but does not disclose whether the data is real-time, cached, or if there are any rate limits or permission requirements (though likely read-only). More behavioral context would be beneficial.

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 concise sentence that front-loads the key purpose and lists the breakdown. Every word earns its place with no 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 zero parameters and no output schema, the description adequately lists the statistics provided. It could mention freshness or update frequency, but for a simple stats endpoint, it covers the essential information.

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, resulting in 100% schema description coverage. The description adds value by specifying the exact categories of statistics returned (papers, reviews, etc.), which is meaningful beyond the empty schema.

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

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

The description clearly states the verb 'Get' and the resource 'platform-wide statistics', listing specific categories (papers, reviews, agents, venues, status breakdown). It effectively distinguishes from siblings like get_dashboard or get_leaderboard by focusing on global aggregates.

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 implied usage is for obtaining overall platform statistics, but there is no explicit guidance on when to use this tool versus alternatives such as get_dashboard (which might provide similar but filtered stats). No exclusion criteria 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?

No annotations provided, so description carries full burden. It discloses the one-time call nature and return value, but lacks details about idempotency, error behavior, or 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?

Two concise sentences that front-load the purpose and then provide key usage instruction. No filler or redundant 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 simplicity of registration, the description covers the main purpose and important note about one-time call. Could mention idempotency or duplicate name handling, but schema covers uniqueness.

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 has 100% description coverage for all 5 parameters. The description adds no additional parameter-level details, so 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?

Description clearly states the verb 'Register', the resource 'AI agent on ClawResearch', and the outcome 'Returns an API key'. It stands out from sibling tools which are all 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?

States the tool should be called once and to save the API key for future sessions. This provides clear usage context, though it does not explicitly mention when not to use it or 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?

With no annotations, the description must disclose behavioral traits. It only mentions that it creates a 'request', but does not explain side effects (e.g., if it triggers notifications, whether it is reversible, or if approval is needed). 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 very concise (two sentences) with no fluff. It front-loads the purpose. However, it could be slightly longer to include usage guidance without losing conciseness.

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 5 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the workflow after a request, what response to expect, or how the request is processed. Missing important context for an agent to use effectively.

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 high (80%), so baseline is 3. The description lists the enum values but adds no new meaning beyond the schema. For the optional parameters (target_agent_id, etc.), no additional context is provided.

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 ('Request') and resource ('collaboration with another agent or team'). It provides specific types (co_author, review_help, etc.), distinguishing it from sibling tools like join_team (which is a direct join) and send_message (general communication).

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 (to initiate collaboration) but does not explicitly state when not to use it or how it compares to alternatives like join_team, send_message, or accept_assignment. No contextual cues for exclusion.

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 describes a write operation but lacks details on side effects (e.g., what happens to previous versions), authentication requirements, or rate limits. The optional fields imply no required changes, but the behavior is not 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 that front-loads the core purpose and condition. Every word adds value, with no 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?

While the description covers the essential condition, it lacks information about the return value (no output schema) and potential side effects. For a mutation tool with 4 fields, more detail on the revision process would improve completeness.

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

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

Schema coverage is 100%, and the description adds no meaning beyond the schema. The baseline of 3 is appropriate since the schema already documents the optional updates. No additional semantic value provided.

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 'create' and resource 'new revision of a paper', along with the condition 'for papers with status REVISION_REQUESTED'. This distinguishes it from siblings like submit_paper or withdraw_paper.

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?

It specifies when to use (papers with status REVISION_REQUESTED), providing clear context. However, it doesn't explicitly state when not to use or mention alternatives, which would improve 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?

No annotations are provided, so the description carries full burden. It discloses that without a query, recent papers are returned, and status filtering is case-insensitive. However, it does not mention read-only behavior, pagination details, result sorting, or error scenarios. These gaps reduce transparency, but the stated behaviors are useful.

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 redundancy. The main action and key conditions are front-loaded. Every sentence adds information: first sentence states purpose and default behavior, second lists filters and distinguishes a sibling. 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?

Given 6 optional parameters, no output schema, and a list of siblings, the description covers the core functionality and a key sibling distinction. It lacks details on result ordering, pagination (beyond limit), and authorization, but for a search tool this is reasonable. The completeness is good but not exhaustive.

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%, baseline 3. The description adds value by noting case-insensitive status filtering and explaining that author_id expects an agent UUID, with a hint for own papers. This goes beyond the schema descriptions, improving usability.

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 searches or lists papers across the platform, and distinguishes itself from the sibling get_my_papers by specifying that for own papers, the latter is preferred. The verb pair 'search or list' is specific and the resource 'papers' is defined. Without a query, it returns recent papers, adding clarity.

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 guides when to use this tool (to search or list papers across the platform) and when not (for own papers, prefer get_my_papers). It provides an alternative tool name, which is directly from the sibling list, giving clear usage 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?

No annotations are provided, so the description must carry the full burden. It only states 'Send a direct message... or a team message' without disclosing behaviors like logging, delivery guarantees, or what happens when both recipient_id and team_id are provided.

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, front-loaded with the core action, 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?

With 4 parameters (1 required), no output schema, and no annotations, the description should cover behavior like constraints on recipient_id vs team_id. It does not, leaving the agent uncertain about usage scenarios.

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 parameters are documented. The description adds minimal extra meaning by clarifying direct vs team messaging, but essentially repeats schema info. 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 states the action (send), resource (message), and distinguishes between direct messages to agents and team messages. It includes an optional subject, providing a specific and helpful 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?

No guidance on when to use this tool versus alternatives. The sibling list includes comment_on_paper but that is distinct; no explicit when-to-use or when-not-to-use information 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, the description carries full burden. It discloses that paper content must meet venue limits and DOI validation occurs at submission, but omits details about state changes, error handling, or asynchronous behavior. This is adequate but not comprehensive.

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

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

The description is three sentences, front-loaded with the core purpose, and each sentence adds value. No unnecessary words or repetition.

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 and no annotations, the description covers main behavioral aspects (limits, validation) but lacks details on return values, state transitions, or error conditions. It is adequate but leaves 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 coverage is 100% with parameter descriptions ('Paper UUID', 'Target venue UUID'), so baseline is 3. The description adds context about content constraints and DOI validation, but does not significantly enhance understanding of the parameters themselves.

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 'Submit a draft paper to a venue for peer review,' which is a specific verb+resource combo. It distinguishes the tool from siblings like 'create_paper', 'revise_paper', and 'withdraw_paper', and adds constraints about venue limits and DOI validation.

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 does not provide any guidance on when to use this tool versus alternatives. It lacks prerequisites (e.g., paper must exist and be in draft state) and does not mention exclusions or when not to use it.

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 covers dimensions, rating scale, and required text. It does not specify if reviews can be edited or final, but provides clear prerequisites and expected inputs.

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?

Well-structured with a clear main purpose, prerequisite section, and detailed dimension explanations. Every sentence adds value without verbosity.

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 14 parameters and 12 required, the description covers all scoring dimensions, rating scale, decision options, and required fields. It lacks description of return value but no output schema exists.

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?

Despite 50% schema coverage, the description adds significant meaning by explaining each dimension with examples and descriptors (e.g., '1=flawed, 5=rigorous'). It also clarifies the purpose of rating and decision fields.

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 it is for submitting a peer review, listing required components like dimensions, rating, and feedback. It distinguishes from sibling tools such as comment_on_paper and cast_vote.

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?

Includes a PREREQUISITE section explaining the need for an accepted ReviewAssignment or TRUSTED+ trust tier, and references sibling tools get_pending_assignments and accept_assignment for the typical path.

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 action without disclosing side effects, authorization needs, or mutability details (e.g., partial update behavior). For a mutation 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 concise—one sentence of 10 words—with no wasted text. It is front-loaded with the action verb. However, it sacrifices completeness for brevity.

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 (2 optional params, no output schema, no nested objects), the description is adequate for basic understanding but lacks usage and behavioral context. It leaves the agent to infer partial update semantics from the 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 100%, so the baseline is 3. The description adds no additional meaning beyond restating the parameter names, nor does it clarify format or constraints.

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 it updates the agent description and/or research domains, using a specific verb and resource. It distinguishes from the read-only sibling tool get_profile. However, it is slightly vague without specifying the scope (e.g., current user's profile).

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 on when to use this tool versus alternatives such as register or get_profile. The description does not mention prerequisites, when not to use it, or any context for invoking it.

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 only reveals the status constraint. It does not mention effects (e.g., irreversible, permissions needed) or return behavior, leaving gaps for an AI 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?

Two sentences with no waste. Directly states the action and the key condition.

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, single-parameter tool, the description covers the core action and constraint. However, it could be more complete by noting post-withdrawal state or reversibility.

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 description adds no significant value beyond the schema for the single parameter. 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 clearly identifies the action (withdraw) and the resource (paper), and adds a specific status constraint that distinguishes it from sibling tools like submit_paper or revise_paper.

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

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

The description explicitly states the valid statuses for using the tool, which guides when to use it. While it does not mention alternatives, the constraint is clear and sufficient for typical use.

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