Iridium

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

The description provides no behavioral details beyond the name. It does not mention consequences of approval, permissions required, or whether the action is reversible. With no annotations, the agent has no insight into the tool's effects.

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

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

The description is overly terse and includes a fragment about HTTP responses that is out of place. It lacks proper structure; every sentence should add value, but this description barely 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 no output schema and 0% schema coverage, the description is entirely insufficient. It fails to explain what approving a comment draft entails, leaving the agent without critical context for correct invocation.

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

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

Schema description coverage is 0%, and the description adds no meaning to the three parameters ('handle', 'comment_at', 'comment_text'). The agent must guess their purpose without any guidance.

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

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

The description states 'Approve Comment Draft', clearly indicating the action (approve) and resource (comment draft). However, it does not differentiate from sibling tools like 'approve_draft' or 'approve_content_draft', which reduces clarity for an AI agent choosing between 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?

No guidance is provided on when to use this tool versus alternatives such as 'skip_comment_draft', 'edit_comment_draft', or 'rewrite_comment_draft'. The description lacks context about prerequisites or use cases.

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, and the description does not disclose any behavioral traits such as side effects, permissions, or state changes. The mention of a 200 response is trivial and does not convey 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 is extremely brief but lacks substance; it is under-specified rather than concise. It repeats the tool name and includes a minor response note, but every sentence fails to provide essential information.

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

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

Given the complexity (3 parameters, no output schema, many sibling tools), the description is completely inadequate. It does not explain the tool's purpose, parameters, or use context, leaving the agent with no actionable understanding.

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?

With 0% schema description coverage and three parameters (handle, post_text, scheduled_at), the description provides no explanation of their meaning or usage. The agent cannot infer semantics from the description alone.

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 merely repeats the tool name 'Approve Content Draft' without adding any specifics about the action or resource. It fails to distinguish from siblings such as approve_comment_draft or approve_draft. Essentially a tautology.

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 like approve_comment_draft, approve_draft, skip_content_draft, or rewrite_content_draft. The description offers no context for invocation.

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 present, so the description must disclose behavior. It only mentions 'Approve Draft' and a 200 response. It does not explain side effects, reversibility, or required permissions for this mutation operation.

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 short but wasteful, including a redundant '### Responses' section with generic response info. It does not earn its space by providing useful details that aid tool selection or invocation.

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

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

Given the tool has two parameters, no annotations, and no output schema, the description is severely lacking. It omits parameter explanations, behavioral notes, and usage context, making it insufficient for correct invocation.

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

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

Schema description coverage is 0%, meaning the schema provides no parameter documentation. The description fails to add any meaning for the two parameters ('handle' and 'override_text'), leaving the agent without context on their purpose or format.

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

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

The description states the tool approves a draft, which is a verb+resource pair, but it does not clarify what type of draft (e.g., general vs. comment vs. content). Given sibling tools like approve_comment_draft and approve_content_draft, the purpose is vague and lacks differentiation.

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

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

There is no guidance on when to use this tool versus alternatives like approve_comment_draft or approve_content_draft. The description provides no context about prerequisites, scenarios, 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?

Describes the operation (pull conversations, repair names) and adds timing (10-30 seconds), which is useful. No annotations provided, but description carries burden well. Could note idempotency or safety explicitly.

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 concise and well-structured: title, bullet points for key uses, and timing. No wasted words, front-loaded with essential info.

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 fully covers purpose, usage, behavior, and timing. Sufficient for agent to select and invoke 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?

No parameters exist, so baseline 4 applies. No additional parameter information needed.

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

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

Description clearly states the tool pulls all existing LinkedIn conversations from Unipile into Iridium, distinguishes from siblings like list_chats and search_chats by emphasizing it's a one-time setup and repair 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?

Explicitly says 'Run this once after connecting LinkedIn to populate your inbox' and mentions fixing blank participant names, providing clear when-to-use guidance.

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

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

No annotations available, and description fails to disclose behavioral traits such as destructive nature, required permissions, or side effects of cancelling a scheduled 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?

Extremely brief but under-specified; the response format example is irrelevant to description purpose and wastes space.

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

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

For a tool with one required parameter, no output schema, and no annotations, the description entirely fails to inform the agent about input format or return behavior.

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?

With 0% schema description coverage and no parameter documentation in the description, the meaning of 'handle' parameter is entirely unclear; description adds zero value 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?

Description is a tautology: 'Cancel Scheduled' merely restates the tool name 'cancel_scheduled' without specifying what scheduled entity is being cancelled or its 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 provided on when to use this tool versus alternatives like reschedule_send, list_scheduled, or other draft-related tools; lacks context for appropriate invocation.

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; description discloses the action (submits code) but lacks details on side effects (e.g., rate limits, error handling, state changes). Response is merely noted as 'Successful Response'.

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?

Concise with clear structure: purpose, usage condition, parameter explanations, and response note. Some repetition of tool name, but overall 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 2FA submission tool with two parameters, the description covers purpose, condition, and parameter origin. Could include more on error cases or response format, but sufficient for typical use.

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 provides no descriptions (0% coverage). The description explains both parameters: account_id as from connect_linkedin_credentials, and code as the verification code from email/phone, adding crucial context 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?

Clearly states it submits a LinkedIn 2FA verification code to complete a connection, distinguishing from sibling tools by specifying it's used after connect_linkedin_credentials returns checkpoint=True.

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 when to use ('after connect_linkedin_credentials returns checkpoint=True'). Does not mention alternatives, but the sequential dependency makes it clear.

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?

Since no annotations, description carries full burden. Discloses that it creates a fresh session and does not affect browser, and mentions 2FA response. However, lacks details on side effects like overwriting existing sessions or error handling.

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

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

Well-structured with clear sections, but includes a boilerplate 'Responses' section that adds little value and extends length unnecessarily.

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?

No output schema or annotations; description explains the 2FA flow but lacks details on error cases, rate limits, or authentication requirements. The omission of the country parameter further reduces 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 0%, so description must compensate. Only username and password are explicitly mentioned in the description; the optional country parameter is completely omitted, leaving its purpose unclear.

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 it connects LinkedIn via username/password, creates a fresh session, and distinguishes from sibling tools like connect_linkedin_li_at and connect_linkedin_checkpoint by specifying the credential-based method.

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?

Provides when to follow up with connect_linkedin_checkpoint for 2FA, but does not explicitly mention when not to use this tool (e.g., for token-based auth) or compare with other connection methods.

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 the tool uses a session cookie for authentication, provides steps to get the cookie, and notes a 200 success response. However, it omits potential side effects, error handling for invalid cookies, or security implications. The information is adequate for a basic understanding but lacks depth.

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 and well-structured: purpose, benefit, step-by-step instructions, and response format. The front-loaded main sentence clearly states the action. Minor redundancy (title repeated) but overall 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 authentication tool, the description covers the main workflow and one parameter, but fails to explain the optional 'country' parameter or any post-connection behavior. The lack of annotation support makes this gap noticeable. It is minimally adequate but not thorough.

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

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

Schema description coverage is 0%. The description explains the 'li_at' parameter in detail, including how to obtain it, but completely ignores the 'country' parameter. With two parameters, half are undocumented, leaving ambiguity for the agent.

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: connecting LinkedIn by pasting a li_at session cookie. It specifies the unique method (cookie-based) and distinguishes it from OAuth, making it clear which of the multiple LinkedIn connection methods this tool represents.

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 explicit instructions for obtaining the required cookie and highlights this method's advantage over OAuth ('Lower friction'). While it doesn't name sibling tools directly, the contrast with OAuth guides the agent on when to prefer this method. It lacks explicit 'when not to use' 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?

With no annotations, the description carries full burden. It discloses the OAuth flow behavior, that no password/cookie is needed, and that connection is confirmed via webhook. It does not mention error handling or rate limits, but for a simple URL-generation tool, transparency is adequate.

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

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

The description is concise: three sentences front-loading the core purpose, with no wasted words. It includes technical details (webhook, no password) efficiently.

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 parameters, the description sufficiently explains what the tool does and how the result is used (URL to open). It lacks explicit return format for failures but covers the primary successful flow well.

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 no parameters (schema coverage 100% trivially), so baseline for 0 params is 4. The description adds no parameter-specific info, but none is needed.

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

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

The description clearly states the tool's function: 'Get a Unipile hosted-auth URL to connect LinkedIn.' It specifies the verb (get) and resource (hosted-auth URL), and distinguishes from siblings like connect_linkedin_credentials by focusing on the OAuth URL method.

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 explains when to use this tool: to obtain a URL for OAuth flow, with details that no password or cookie is needed. However, it does not explicitly compare with alternative LinkedIn connection methods (e.g., connect_linkedin_li_at), leaving the agent to infer context from sibling names.

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 description fails to disclose any behavioral traits (e.g., safety, side effects, or whether it is destructive). No value added.

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 short but contains a verbose '### Responses' section that is likely a formatting artifact. It fails to be usefully concise.

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

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

With no output schema, no annotations, and no parameter descriptions, the tool's context is severely incomplete. Agent lacks information to invoke it correctly.

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

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

Schema description coverage is 0%, and the description adds no meaning to the parameters (name, steps). Agent cannot infer their purpose 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 only says 'Create Sequence' and includes a redundant response section. It does not explain what a sequence is or how it relates to sibling tools. Purpose is vague.

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 'enroll_prospect' or 'run_outreach_pipeline'. No context provided.

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

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

With no annotations provided, the description fully discloses behavioral traits: immediate deactivation, session destruction, subscription cancellation, automation stop, data retention for 30 days then permanent erasure, and action history retention for audit. This covers all key 'destructive' aspects transparently.

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 and well-structured. It starts with the title and a clear sentence, then uses bullet-style paragraphs to list consequences. Every sentence adds essential information 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 destructive tool with no parameters and no output schema, the description covers all relevant context: immediate effects, data retention policies, audit trail, and response type. It is complete for an agent to understand the tool's impact fully.

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

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

The tool has zero parameters, so the schema contributes nothing. The description adds comprehensive context on what the tool does and its effects, fulfilling the need for parameter explanation. 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 explicitly states the tool's purpose: 'Delete your Iridium account.' It details specific actions (deactivation, session destruction, subscription cancellation) and data handling, clearly distinguishing it from all sibling tools which involve drafting, scheduling, or connecting, not deletion.

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 implicitly conveys that this is a final, irreversible action by listing consequences (immediate stop of automation, data erased after 30 days). However, it does not explicitly state when to use vs. not use, nor mention any alternatives or prerequisites, which would be helpful for a destructive tool.

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

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

With no annotations provided, the description carries full burden and discloses side effects: removes connection from Unipile, clears profile, and stops pipelines. This is adequate for a simple 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?

Description is short and front-loaded with the main action. The 'Responses' section adds minor noise but overall structure is acceptable.

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 covers the effect and reversible nature ('until reconnected'). Missing info on idempotency is minor.

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, so baseline 4 per rules. Description does not need to add parameter details.

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 'disconnect' and the resource 'LinkedIn account', distinguishing it from sibling connect tools like connect_linkedin_*.

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 disconnect) and notes consequences (pipelines stop), but lacks explicit exclusions or alternatives. Still, context is clear among siblings.

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 fully discloses key behaviors: data is fetched live from LinkedIn, accuracy details, suggested_send_at is non-binding, drafts stay pending, and the profile structure is described. This gives complete transparency about side effects and data quality.

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 paragraphs and Args list. Front-loaded with core purpose. Every sentence adds value. Slightly longer than necessary due to response section, but that section is justified given no output schema.

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 3 params, no annotations, no output schema, the description covers purpose, usage, behavior, parameter semantics, and return shape comprehensively. It even includes data accuracy and draft lifecycle details, leaving little ambiguity.

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?

With 0% schema coverage, the description's Args section adds needed meaning: query with example, location with example, limit with range and default. The descriptions are helpful but could be slightly more precise about query syntax (e.g., does it support AND/OR?). Still excellent compensation.

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 it searches prospects, enriches profiles, and generates connection note drafts. Distinguishes from sibling run_outreach_pipeline by describing it as a complement for instant vs. scheduled use. The verb 'discover' combined with specific actions makes the purpose unmistakable.

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 positions the tool as a complement to run_outreach_pipeline, indicating when to use it for instant search instead of scheduled runs. While not providing exhaustive when-not conditions, the context is clear enough for agents to decide.

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 like idempotency, side effects, or required permissions. It only mentions a 200 response, failing to provide essential 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?

While short, the description is not efficiently structured; it includes a heading and a response section that add no value. It fails to convey necessary information in a concise manner.

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 output schema and only 2 parameters, the description should provide comprehensive context. It does not explain tool behavior, prerequisites, or relation to drafts, rendering it 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?

The description adds no meaning beyond the input schema. Schema description coverage is 0%, and the description does not explain the 'handle' and 'updated_content' parameters, leaving ambiguity about their semantics.

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

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

The description merely restates the tool name 'Edit Comment Draft' without specifying what editing entails or distinguishing it from sibling tools like rewrite_comment_draft or approve_comment_draft.

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 rewrite_comment_draft or approve_comment_draft. The description lacks any context for decision-making.

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 present; description does not disclose any behavioral traits (e.g., idempotency, permissions, side effects). Agent has no information to gauge impact of invocation.

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?

Extremely brief but fails to convey purpose or usage. The response status snippet is irrelevant without context. Conciseness is wasted when no information is provided.

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?

No output schema, no description of return values or errors. Given the tool's function (enrolling a prospect), critical details like success indicators or duplicate handling are missing.

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 zero description coverage; description adds no meaning to 'prospect_handle' or 'sequence_handle'. Parameters remain opaque strings with no format or usage hints.

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 is essentially the tool name, providing no clarification on what 'enroll' means. It does not distinguish from sibling tools like 'create_sequence' or 'discover_prospects'.

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 'discover_prospects' or 'search_prospects'. No context about prerequisites or scenario suitability.

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 'Get Draft Detail' and mentions a 200 response, lacking any behavioral traits like read-only guarantees, error handling, or authorization needs.

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

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

The description is extremely brief (one line plus response header), but it is under-specified rather than concise. Important information is missing, making it inefficient for agent use.

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 the tool's simplicity (one param, no output schema), the description lacks essential details about the parameter, response content, and usage context, leaving the agent with insufficient 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?

The single parameter 'handle' has no description in the schema (0% coverage) and the tool description provides no explanation of its meaning or format. The agent is left to guess.

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 Draft Detail' clearly indicates the tool retrieves details of a single draft, distinguishing it from list_drafts (list all) and other draft actions. The verb+resource is specific.

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 siblings like list_drafts or other draft actions. Missing context about prerequisites or scenarios.

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 full transparency burden. It mentions returns are enriched data but does not disclose rate limits, authentication requirements, error handling (e.g., no match), or whether the tool is idempotent. The description lacks sufficient 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 is well-structured with a clear purpose, required conditions, optional hints, and a bullet-like list of returned fields. It is front-loaded and concise, though could be slightly more compact.

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 7 parameters, no output schema, and no annotations, the description explains parameters and return fields adequately. However, it omits details like result limits, pagination, error behavior for no matches, and precise field formats, leaving some gaps for effective agent use.

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 0%, requiring the description to add meaning. It explains that name, linkedin_id, iridium_handle are primary identifiers and company, education, etc. are optional hints, which adds significant value beyond the schema types. However, it does not specify exact formats (e.g., linkedin_id format).

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 'look up LinkedIn profile(s) for a person' and specifies required identifiers (name, linkedin_id, iridium_handle) and optional hints. It is distinct from sibling tools like get_user_profile or discover_prospects.

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 explains that at least one of three identifiers must be provided and optional hints narrow the search, but it does not explicitly indicate when to use this tool over alternatives or when not to use it (e.g., for own profile vs. others). Usage guidance is implied but 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, the description merely implies a read operation via the name and includes a response example, but does not disclose any behavioral traits like authentication requirements, rate limits, or potential side effects.

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

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

The description is very short and includes only the core purpose and a response snippet. While concise, the response formatting adds little value and could be better 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 fails to explain what the user profile contains or how it is structured. The response example is vague ('Successful Response') and provides minimal context.

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

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

There are no parameters, and schema coverage is 100%, so baseline 3 is appropriate. The description adds no additional meaning beyond the schema, but it's not needed for no parameters.

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

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

The description states 'Get User Profile' which clearly identifies the action and resource, but it does not differentiate from sibling tools like 'get_linkedin_profile' or clarify what 'profile' refers to (e.g., internal vs public 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 is provided on when to use this tool versus alternatives, such as when to retrieve a LinkedIn profile vs a user profile. No context on prerequisites or limitations.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It merely says 'List Chats' and includes a generic response section. It does not mention pagination, rate limits, required permissions, or data freshness. The tool is likely a read-only operation, but this is not explicitly stated.

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, containing only 'List Chats' and a response section. However, the response section adds little value and could be omitted. The structure is front-loaded but the unnecessary response detail reduces 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?

Given the absence of output schema, annotations, and parameters, the description should explain what 'chats' refers to and the structure of the response. It does not, leaving the agent without sufficient context to understand the tool's output or its place among siblings.

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 no parameters in the input schema, and schema description coverage is 100% (empty schema). Per guidelines, baseline for no parameters with high coverage is 3. The description adds no parameter-related information, but none is needed since there are no parameters.

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

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

The description states 'List Chats' which is a specific verb+resource pair. It clearly indicates the tool lists chats. However, it does not differentiate from sibling tools like list_comment_drafts or list_drafts, leaving ambiguity about what constitutes a 'chat' versus other listable entities.

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

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

There is no guidance on when to use this tool versus alternatives such as search_chats or other list tools. The description provides no context about prerequisites, typical use cases, 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, description clarifies read-only behavior (no modifications) and output format (full display). Could explicitly state no side effects, but sufficient.

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?

Reasonably concise, front-loaded with purpose. The example formatting is helpful but slightly verbose. Still efficient overall.

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?

Complete for a simple list tool: explains what it does, how to display results, and what actions to avoid. No output schema but description covers return behavior.

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, so baseline 4. Description adds no parameter info but none needed; schema coverage is 100%.

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

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

The description states 'List pending comment drafts awaiting review', which is a clear verb+resource. It distinguishes from sibling tools like approve_comment_draft and edit_comment_draft by focusing only on listing.

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 instructs to always display drafts in full and warns not to call approve_comment_draft without user request, providing clear when-to-use and when-not-to-use guidance.

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

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

Annotations are absent, so the description must convey behavioral traits. It only states 'List Content Drafts' and shows a response schema snippet, omitting whether the operation is read-only, requires authentication, or has limitations. The agent cannot infer safety 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?

The description is extremely short but includes a redundant response section that does not aid tool selection. It is concise but not optimally structured—it could omit the responses block and add a brief clarification of what content drafts are.

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

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

Despite having no parameters or output schema, the description does not explain what content drafts are or how the list is ordered/paginated. With siblings like get_draft_detail and approve_content_draft, more context is needed for complete usability.

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 no parameters (0), and schema coverage is 100% vacuously. Per the rubric, 0 parameters yields a baseline of 4. The description adds nothing beyond the schema, but no additional meaning is needed.

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

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

The description clearly states 'List Content Drafts', which is a specific verb+resource combination. It effectively distinguishes from sibling tools like list_drafts and list_comment_drafts by specifying the resource type (content drafts).

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention any filtering or context that differentiates it from list_drafts or list_comment_drafts, leaving the agent without decision-making information.

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 exist, so the description must carry the full burden. It only states 'List Drafts' and includes a response format note, but fails to disclose any behavioral traits such as scope, pagination, or permissions.

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

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

The description is extremely short but not effectively concise; it is under-specified. The response format note is unnecessary for the agent and wastes space. Key information is missing.

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 zero parameters, the description should clarify the tool's scope (e.g., all drafts vs. filtered). It lacks completeness for an agent to use it correctly.

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

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

With zero parameters and 100% schema coverage (trivial), the description does not need to add param details. Baseline 4 is appropriate, though no additional meaning 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 'List Drafts' is a tautology of the tool name. It does not specify whether it lists all draft types (comment, content, etc.) or just generic drafts, failing to distinguish from siblings like list_comment_drafts and list_content_drafts.

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 over the more specific list tools. There are no exclusions or context cues to help the agent decide.

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 description does not disclose any behavioral traits (e.g., read-only, pagination, auth needs). Only mentions a 200 response with no further detail.

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, but includes unnecessary response header detail. Lacks structured information beyond the tool name.

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?

No output schema, no description of return values. The '200 Response' mention is insufficient. The tool's purpose is under-specified.

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, so baseline is 4, but description adds no meaning about the output or scope. It merely states 'List Replies' without defining what a 'reply' is.

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 is only 'List Replies' without specifying what kind of replies (comments, chats, etc.). It does not distinguish from sibling tools like list_chats or list_comment_drafts.

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. With many list tools, the agent has no 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 should disclose behavioral traits (e.g., read-only nature, pagination, sorting). However, it only mentions a response format, leaving the agent uninformed about side effects or limitations.

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

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

The description is extremely brief, but it is not truly concise because it omits essential context. It provides only a title and a response status line, which is under-specification rather than efficient communication.

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 (0 params, no output schema), the description should at minimum state the entity being listed (e.g., 'List all scheduled sends'). It fails to do so, making the tool's purpose ambiguous.

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 0 parameters, so baseline is 4 per guidelines. The description adds no information beyond the schema, but the schema is trivial (empty). A more helpful description would clarify what is being listed, but the baseline 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 simply says 'List Scheduled', which is vague and does not specify what type of scheduled items (e.g., messages, posts, drafts). It fails to clearly state the resource being listed, making it hard to distinguish from similar tools like list_drafts.

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 (e.g., cancel_scheduled, list_drafts). The description does not include any context about prerequisites or use cases.

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?

Lacking annotations, the description should disclose that this is a read-only operation with no side effects. It only mentions a 200 response, which 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 very short but includes a redundant code block about a 200 response. It is concise but under-specified.

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

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

For a tool with no parameters and no output schema, the description should still mention the scope (e.g., 'lists all MCP tools in the system'). It fails to provide 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?

No parameters exist, so schema coverage is 100%. The description adds no value beyond the schema; baseline is 4 but not earned due to lack of clarification on what 'tools' includes.

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 'List Tools' clearly states the verb and resource, and the tool is distinct from siblings like list_chats or list_drafts. However, it could be more specific (e.g., 'List all available MCP 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?

No guidance on when to use this tool vs alternatives. The description does not provide context 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 only states the action and parameters, omitting important behavioral details such as side effects (e.g., overwriting original time), error conditions (e.g., send already sent, past time), or authentication requirements. The response section mentions 200 success but no errors.

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 reasonably concise, with a clear sentence for the action followed by parameter explanations. It includes a response section, but overall the structure is easy to parse and each part serves a 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 no output schema and no annotations, the description lacks completeness. It does not cover error handling, idempotency, rate limits, or constraints on the send_at value (e.g., cannot be in past). The tool is simple but the description is barely adequate for safe 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?

Schema coverage is 0%, so the description must compensate. It adds meaningful context for both parameters: 'handle' is explained as coming from list_scheduled, and 'send_at' includes an ISO-8601 format example. This provides value beyond the bare 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 ('Reschedule a pending send to a different time'), specifying the verb and resource. It distinguishes from sibling tools like 'cancel_scheduled' and 'list_scheduled' by focusing on rescheduling rather than canceling or listing.

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 pending sends and references 'list_scheduled' for obtaining the handle, but does not explicitly state when not to use (e.g., vs. cancel_scheduled) or provide exclusion criteria. Guidance is implicit rather than explicit.

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

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

No annotations exist, and the description fails to disclose any behavioral traits such as side effects, required permissions, or what the tool does beyond its 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 extremely short but at the cost of omitting essential information. It is under-specified rather than efficiently concise.

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

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

Given the presence of multiple sibling tools and the lack of output schema, the description fails to provide necessary context for correct invocation. It is completely inadequate.

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 0% description coverage, and the description adds no meaning to parameters 'handle' and 'instruction'. Their purpose is entirely unclear.

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 is merely 'Rewrite Comment Draft', which restates the tool name and provides no specific verb+resource detail. It does not distinguish this tool from siblings like 'edit_comment_draft' or 'rewrite_draft'.

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. There is no mention of context, 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?

No annotations exist, so the description must disclose behavioral traits. It provides none—no mention of side effects, idempotency, authorization needs, or output behavior.

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

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

The description is extremely short but lacks meaningful content. It is under-specified rather than concise, with a stray response code that adds no 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?

Given the lack of annotations, output schema, and parameter descriptions, the description is entirely inadequate. It does not help an agent understand the tool's role or correct invocation.

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

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

Schema description coverage is 0%, and the description does not explain the parameters (handle, instruction) or their expected values. The agent receives no semantic help beyond the parameter names.

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 merely repeats the tool name 'Rewrite Content Draft' and includes a response status code snippet. It fails to specify what the tool does, what resources it acts on, or how it differs from siblings like 'rewrite_draft' or 'rewrite_comment_draft'.

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. Sibling tools exist (e.g., rewrite_draft, rewrite_comment_draft) but the description offers no 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 and no description beyond the title, there is no disclosure of behavioral traits such as whether the tool is destructive, requires authentication, or has rate limits. The response section only mentions a 200 HTTP status without further detail.

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

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

The description is extremely short but includes an irrelevant section about HTTP responses that does not aid tool understanding. It is under-specified rather than concise, as it lacks 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 no output schema, no annotations, and 37 sibling tools, the description is severely incomplete. It does not explain the tool's purpose, behavior, or return value, leaving the agent with no actionable context.

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

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

Schema description coverage is 0%, and the description does not add any meaning to the two required parameters 'handle' and 'instruction'. It fails to explain what each parameter represents or how it should be used.

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 is merely 'Rewrite Draft', which is a tautology of the tool name. It does not specify what rewriting a draft entails, nor does it differentiate from sibling tools like rewrite_comment_draft or rewrite_content_draft.

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 lacks context about typical usage scenarios 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?

Despite no annotations, the description details post-call behavior: always display drafts in full, do not auto-approve or schedule. It also mentions the response format (200). Covers major behavioral traits well, though no edge cases or error handling.

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

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

Well-structured with clear sections (purpose, usage, post-call instructions, response). Front-loads key actions. Slightly verbose with example list, but overall 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?

Given zero parameters, no output schema, and no annotations, the description covers the tool's purpose, usage rules, and expected post-call behavior. Missing error handling, but sufficient for a simple generate-and-display tool.

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 100%), so baseline is 4. The description adds no parameter info, but none is needed.

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

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

The description clearly states the verb (generate), resource (comment drafts on relevant posts), and scope (searches all LinkedIn, user's saved topics). It explicitly distinguishes itself from the sibling run_company_commenting_pipeline by specifying when not to use.

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?

Provides explicit usage conditions: 'USE THIS when the user wants to comment by TOPIC' with examples, and 'DO NOT USE when the user names specific companies' with alternative tool reference. This gives clear guidance on when to select this tool vs. alternatives.

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

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

Discloses that the tool searches by author company and recency only, no keyword filter, and that ANDing a keyword returns nothing. Notes that zero drafts is a valid outcome. However, lacks details on rate limits or authentication needs, but given no annotations, it is 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?

Well-structured with clear sections, but slightly verbose. Could be more concise while retaining all information. However, it is front-loaded with purpose and each sentence is useful.

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?

Covers purpose, usage, behavior, parameters, response handling, and edge cases (zero drafts, unresolved companies). No output schema exists, but description adequately explains what the user gets. Complete for a 3-parameter tool.

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 0%, but the description includes an 'Args:' section explaining each parameter (companies max 5, n default 3, date_posted options with default). This fully compensates for missing schema descriptions.

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

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

The description clearly states the tool generates LinkedIn comment drafts on recent posts by people at specific companies. It distinguishes from sibling tool run_commenting_pipeline by specifying that this tool searches by company and recency, not by keywords.

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

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

Explicitly says 'USE THIS when the user names one or more companies' with examples, and 'DO NOT USE for topic- or keyword-based commenting' directing to run_commenting_pipeline. Also discusses valid outcome of zero drafts and how to handle unresolved companies.

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 exist, and the description fails to disclose any behavioral traits (e.g., side effects, permissions required, whether it is destructive or 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?

Extremely short but lacks substance. The response section is filler. Under-specification, not true 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?

Complete lack of context. With no params, no output schema, and no annotations, the description should define what the tool does, but it doesn't.

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 in schema, so coverage is trivial. Description adds no meaning—it does not explain the tool's purpose or behavior, which is needed since parameters are absent.

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 merely restates the name 'Run Content Pipeline' and includes an auto-generated response section. No explanation of what the content pipeline is or what running it 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 on when to use this tool versus siblings like run_commenting_pipeline or run_outreach_pipeline. No context or usage advice 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool is synchronous, returns 3 drafts, and takes about 5 seconds. However, it does not mention any prerequisites, dependencies, or error handling, but the main behavioral traits are covered.

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 and front-loaded with the purpose. It includes a necessary code block for display instructions, which is somewhat verbose but justified to ensure correct agent behavior. Overall, it is well-structured and not overly long.

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 explains the return format in detail (drafts with name, headline, note text, suggested send time). It covers the tool's execution behavior and post-call instructions. However, it could mention what input or context the pipeline uses, but for a parameterless tool it is fairly 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?

There are zero parameters, so the baseline score is 4. The description adds value by explaining what the tool does and its output behavior beyond the empty schema, which is adequate for a parameterless tool.

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 runs an outreach pipeline that returns 3 connection note drafts inline in ~5s. The verb 'run' and resource 'outreach pipeline' are specific, and the outcome is explicitly described, distinguishing it from sibling tools like run_commenting_pipeline or run_content_pipeline.

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 explicit instructions: always display every draft to the user in full and never call approve_draft or schedule unless the user explicitly asks. This tells the AI agent when to use the tool and what not to do afterward, which is clear guidance for correct behavior.

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 does not disclose behavioral traits such as whether scheduling overrides existing messages, requires authentication, or has side effects.

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

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

The description is extremely short but includes irrelevant response format details. It fails to convey essential information, making it under-specified rather than concise.

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

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

Given no output schema, the description should explain return values. It only mentions a 200 response without any details. For a scheduling tool, critical details about timing and confirmation are missing.

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

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

Schema description coverage is 0%, so the description must explain parameters. It does not. 'send_at' is nullable but its purpose and format are left ambiguous. No value added beyond parameter names.

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 only repeats the tool name and includes a response header, but does not state what the tool does. It lacks a verb and resource, and fails to distinguish from siblings like schedule_dm_to_person.

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., schedule_dm_to_person, schedule_manual_dm, reschedule_send). The description provides no 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?

No annotations are provided, and the description offers no behavioral details (e.g., side effects, permissions, idempotency). The tool could be destructive or read-only; there is no indication.

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?

Extremely brief, but not concise in a helpful way. It lacks critical information; brevity here is underspecification, not 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?

With 5 parameters, no output schema, no annotations, and many sibling tools, this description is grossly insufficient for an AI agent to understand or 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?

Schema description coverage is 0%, and the description does not explain any parameter meaning or constraints. The five parameters are left entirely to the schema, which has only names and types.

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 merely repeats the tool name and includes a generic HTTP status note. It does not state what action the tool performs or what resource it affects, making it a tautology.

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 usage context, conditions, or alternatives are mentioned. Sibling tools like schedule_manual_dm and schedule_chat_reply exist but are not differentiated.

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 disclose behavioral traits. It implies mutation (scheduling a message) but does not mention authentication requirements, rate limits, or what happens if the user is not connected. The behavior is minimally described.

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 well-structured with a clear purpose, an Args section, and a response note. It is relatively concise, though the 'Responses' section could be omitted as it adds little 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?

Given the lack of annotations and output schema, the description covers each parameter and format. However, it does not describe the response content beyond a status code, leaving the agent unsure about success indicators.

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 0%, so the description must compensate. It explains chat_handle as from list_chats/list_replies, text as message text, send_at as ISO-8601 format, and message_type with default and options. This adds significant 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 ('Schedule a direct message') and the resource ('someone you're already connected with'). It provides a prerequisite (list_chats for chat_handle). However, it does not differentiate from the sibling tool 'schedule_dm_to_person'.

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 guides the user to use list_chats to find the chat_handle, which is helpful context. However, there is no guidance on when not to use this tool or alternatives like schedule_chat_reply.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It fails to indicate whether the operation is read-only, destructive, requires authentication, or has any side effects. The minimal text offers no 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 is very short but lacks substance. The response format section is generic and does not convey tool-specific structure. It is under-specified, not efficiently concise.

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

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

Given the lack of output schema and low schema coverage, the description is wholly inadequate. It does not explain what the tool returns, how to use the single parameter, or how it fits within the broader toolset.

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 0% and the description does not explain the 'name' parameter. The agent is left to guess whether 'name' is a search query, a chat identifier, or something else.

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 only restates the tool name 'Search Chats' and adds a standard HTTP response note. It does not specify what 'search' entails (e.g., full-text, by name) or how it differs from sibling 'list_chats', which likely lists all chats.

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 'list_chats' or 'search_prospects'. The description provides no context, 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?

No annotations are provided, and the description fails to disclose any behavioral traits. It only mentions a 200 response status without describing the effect of the operation, return format, or side effects. The agent has no insight into whether this is a read or write operation.

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

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

The description is extremely short, but this is due to under-specification rather than efficient clarity. It contains only a title and a redundant status note, wasting the opportunity to inform the agent.

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 3 parameters, no output schema, no annotations, and no sibling differentiation, the description is completely inadequate. The agent lacks essential context 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 has 0% description coverage for parameters, yet the description adds no explanation of 'query', 'location', or 'limit'. The agent cannot infer the meaning or expected format of these parameters from the description.

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 only states 'Search Prospects', which is a tautology that repeats the tool name. It does not define what a prospect is or clarify the search scope, nor does it distinguish this tool from siblings like 'discover_prospects'.

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 usage guidance is provided. There is no indication of when to use this tool over alternatives, no prerequisites, and no examples of appropriate contexts.

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, and the description does not disclose any behavioral traits such as whether the action is reversible, prerequisites, 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?

The description is extremely short, but it is not meaningfully concise—it omits essential information. The inclusion of a response stanza is irrelevant without 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 tool with one parameter, the description still fails to convey the basic purpose or any operational context, making it completely inadequate.

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 single required parameter 'handle' has no description in the input schema, and the tool description adds no explanation of its meaning or expected format.

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 merely repeats the tool name in a header and then describes a 200 response. It does not state what the tool does (e.g., skip a specific comment draft), nor does it distinguish it from siblings like approve_comment_draft or edit_comment_draft.

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 offers no context for invocation.

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, and the description gives no information about side effects, prerequisites, or behavior beyond the trivial status code.

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?

While brief, the description is under-specified to the point of being useless. It lacks any substantive content that would help an agent.

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 for a simple tool with one parameter, the description must at least indicate the intended action. It completely fails to provide necessary context.

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

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

The single 'handle' parameter is not described. Schema coverage is 0%, and the description does not clarify its meaning or expected format.

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 only repeats the tool name and includes a response code but does not state what the tool does. It fails to convey the action of skipping a content draft.

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 siblings like skip_draft or skip_comment_draft. No context provided for usage scenarios.

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 and description only mentions a 200 response. Does not disclose whether the action is destructive, reversible, requires permissions, or any 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?

Extremely brief but incomplete. Includes unnecessary response format details, lacking essential purpose and usage info. Not concise in a helpful way.

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 annotations, no output schema, and minimal description, the tool definition is severely inadequate for an agent to use 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?

Single parameter 'handle' has no schema description and description does not explain its meaning, format, or purpose. 0% schema coverage and no param info in description.

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 is only 'Skip Draft', which is a tautology. It does not specify what type of draft or the action's effect, nor distinguishes from sibling tools like skip_comment_draft or skip_content_draft.

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 instead of alternatives. Sibling tools exist with more specific names, but no context is provided 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 must disclose behavioral traits. It only notes a 200 response, omitting whether the operation is destructive, requires authentication, or has side effects. Critical transparency is absent.

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

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

The description is extremely short but wastes space on a redundant 'Responses' section. It is under-specified rather than concise, offering no meaningful content beyond the tool name.

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 12 parameters and no output schema, the description should explain the tool's effect and context. It does not mention what settings are updated, the expected outcome, or any dependencies, making it completely inadequate.

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

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

Schema description coverage is 0%, yet the description adds no parameter explanations. While some parameter names are self-explanatory, the description fails to clarify format, allowed values, or relationships, leaving the agent to infer entirely from names and types.

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 'Update Settings' is a tautology that restates the tool name without specifying what settings (e.g., user, account, or system settings) are being modified. The parameter names hint at content/commenting settings, but the description fails to clarify the scope or resource.

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 sibling tools. There are no conditions, prerequisites, or alternatives mentioned, 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.