LinkedIn MCP Server (Salesbot)

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

The description discloses key behaviors beyond annotations: automatic blacklist/domain filtering, duplicate checks, manual exclusion, scheduling of visit→connect→message steps, and return of counts added vs filtered. Annotations provide idempotentHint=true and destructiveHint=false, which align with this non-destructive, idempotent behavior. The description adds significant 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 two sentences, front-loaded with the main action and key constraints. The second sentence explains automatic steps and return value. No unnecessary words. Highly concise and 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 explains the return value (added vs filtered). It explains the side effects (scheduling campaign steps). However, it does not mention error conditions (e.g., invalid campaign_id, non-existent contacts) or prerequisites (e.g., campaign must be in a certain state). It is fairly complete but has minor gaps.

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

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

The input schema has 100% description coverage with 'UUID of the campaign' and 'Array of contact UUIDs to add'. The description adds no extra semantic meaning beyond confirming contacts are selected by ID. Thus, it meets the baseline of 3 but does not exceed.

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 adds selected contacts to an existing campaign, specifying the verb 'add' and the resource 'contacts to campaign'. The title 'Add contacts to campaign' reinforces this. It distinguishes from siblings like 'create_campaign' (creates new campaign) and 'start_campaign' (starts existing campaign).

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

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

The description implies usage when you have an existing campaign and want to add contacts. It says 'to an existing campaign', indicating the campaign must exist. However, it does not explicitly state when not to use it (e.g., if campaign is already completed) or mention alternatives like creating a new campaign. Still, the context is 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?

Annotations indicate it's a non-destructive mutation. The description adds behavioral details: key generation from label and allowed types. It does not contradict annotations. Full disclosure of side effects (e.g., duplicate behavior) is absent, but the key generation is a valuable addition.

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

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

Two concise sentences: first states purpose with example, second covers type options and key generation. No redundant words; information is front-loaded and efficient.

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

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

Given the two-parameter schema and no output schema, the description covers core functionality well. However, it lacks discussion of edge cases like duplicate field names or whether the operation updates existing fields. Still mostly complete for straightforward usage.

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

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

Schema coverage is 100%, and the description enhances understanding by explaining the 'type' enum with defaults and the key generation process from 'label'. This adds meaning beyond the 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 action 'Add', the resource 'custom field to CRM leads', and provides an example. It distinguishes from siblings like 'set_lead_fields' and 'list_crm_fields' by specifying it adds a new field definition.

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 adding new custom fields but provides no explicit guidance on when to use vs alternatives like 'set_lead_fields' or handling potential duplicates. No when-not-to-use criteria are mentioned.

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

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

Beyond annotations (which correctly indicate non-destructive), the description adds behavioral context: key auto-generation, optional color formatting, and append-only placement. This helps the agent understand the tool's effect without contradiction.

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?

Three concise sentences front-load the action and parameter details. Every sentence contributes essential information without redundancy or excess.

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 two parameters and no output schema, the description fully covers purpose, parameter semantics, and behavioral outcome (append to end). No gaps remain.

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 100% schema coverage, the baseline is 3. The description adds value by explaining that a key is generated from the label and providing an example hex color format, which aids correct parameter formatting.

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 ('Add'), the resource ('pipeline stage'), and provides specific details: label generation, optional color, and position ('appended to the end'). It distinguishes from siblings like 'rename_crm_stage' and 'delete_crm_stage'.

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

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

Usage is implied from the action ('Add a new pipeline stage'), but no explicit guidance on when to use vs. alternatives, prerequisites (e.g., pipeline existence), or when not to use. The description lacks exclusionary or comparative language.

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

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

The description thoroughly discloses behavioral traits: it enforces daily limits and allowed hours, includes a quality check that can be bypassed, and describes the conditional rewrite flow. Annotations only provide idempotent and destructive hints, so the description adds substantial value without contradiction.

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 front-loaded with the primary action, then details optional edits and quality check. Each sentence adds essential information without redundancy or waste.

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

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

While main behaviors are covered, the description lacks details on return values (no output schema) and edge cases like daily limit exceeded or hours restriction behavior. It adequately covers the standard flow but has gaps for completeness.

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

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

All parameters are described in the schema (100% coverage). The description adds context beyond schema by explaining the default behavior of skip_gpt_check and the effect of edited_messages, enhancing understanding.

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

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

The description clearly states that the tool approves a draft and hands it to the campaign executor for sending, with specific verbs and resources. It distinguishes from siblings like 'reject_message' by describing the approval workflow, including optional edits and quality checks.

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

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

The description implies the tool is for approving drafts but does not explicitly state when to use it versus alternatives like 'reject_message' or 'list_pending_approvals'. There are no when-not-to-use or exclusion signals.

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?

Description adds that tool can change status to done, open, or cancelled, and defaults to done. Annotations already indicate idempotent and not destructive; description aligns and adds context without contradiction.

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

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

Two sentences, no fluff. First sentence states action and defaults; second gives usage guideline. Information is front-loaded and efficient.

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

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

For a simple status-update tool with no output schema, description covers parameters and usage context. Could mention response format, but not required. Adequate given tool simplicity.

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

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

Schema coverage is 100%, so baseline 3. Description repeats schema info (status default) and adds minimal extra context ('after a follow-up is handled'). No new parameter-level details beyond 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 clearly states verb (mark/update) and resource (CRM task) with specific statuses (done, reopen, cancel). Distinguishes from siblings like create_task by implying this is for existing tasks.

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 after a follow-up is handled', providing clear context. Does not list alternatives, but siblings are implicitly different (e.g., create_task for new tasks).

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 link is valid for ~2 hours, white-labeled, and requires user to open it in a browser. No contradiction with annotations (idempotent, not destructive). Adds context beyond annotations regarding link time limit and interaction flow.

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?

Three sentences front-loading purpose, then usage, then parameter details. No unnecessary words. Every sentence adds value.

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

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

For a simple tool with 2 optional params and no output schema, the description fully covers what the tool does, when to use it, how parameters affect behavior, and what the user needs to do (open the link). No gaps.

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

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

Schema coverage is 100%. Description adds meaning: reconnect is for reconnecting a blocked/expired account, profile_id defaults to active/first. These details are not in the schema descriptions, providing valuable context.

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 generates a secure LinkedIn connect/reconnect link for authentication. Distinguishes from sibling tools like send_connection_request and get_linkedin_status by focusing on link generation rather than sending requests or checking status.

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 specifies when to use: when get_linkedin_status shows not connected/blocked, or after specific errors. Also explains optional parameters and the reconnect flag. Provides clear context and implicitly guides against misusage.

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 draft status and that it does not start sending until activation. Annotations only indicate non-read-only and non-destructive; description adds crucial behavioral context beyond annotations.

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

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

Three sentences, front-loaded with essential info (draft status, required fields). No redundancy or fluff.

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?

Returns campaign_id is stated. Nested step objects are explained. Linking to sibling tool 'add_contacts_to_campaign' provides context. Optional parameters like daily_limit and sender_context are omitted but schema covers them.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by summarizing required parameters, explaining step structure, and mentioning AI/template settings, which aids understanding beyond schema property 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?

Description clearly states 'Create a NEW campaign' with specific verb and resource, and adds key detail that it's saved as draft. Distinguishes from sibling 'start_campaign' which activates a campaign.

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 recommends using 'add_contacts_to_campaign' next, and implies that after creation and adding contacts, the user must activate in the app. Could be improved with when-not-to-use or alternatives.

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

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

Annotations already indicate non-readonly and non-destructive. Description adds that it creates a task and optionally links to a lead, plus the Pro plan constraint. No contradictions, but does not disclose additional behaviors like idempotency.

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

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

Single sentence with example and note. Extremely concise, front-loaded with purpose, no wasted words.

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

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

Adequately covers core purpose, optional linking, and plan restriction. Given 4 params with full schema coverage and no output schema, description is sufficient for an agent to understand basic usage.

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

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

Schema coverage is 100%, so baseline 3. Description reinforces purpose of title and contact_id with example, but adds no new syntax or format details 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 verb 'Create' and resource 'task', with optional linking to a lead. Example clarifies usage. Distinguishes from siblings like 'complete_task' and 'list_tasks'.

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?

Implies usage by mentioning 'Pro plan only', but does not explicitly state when to use vs alternatives or when not to use. No exclusion criteria or comparison to other tools.

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 include destructiveHint: true and idempotentHint: true. The description adds valuable behavioral context: values stay in place but are no longer shown, which goes beyond what annotations provide.

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

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

Two concise sentences, front-loaded with the action, no wasted words. Every sentence adds value.

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

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

Given the tool's simplicity (one required parameter, no output schema), the description is fully complete. It explains the effect on data, which is sufficient 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 coverage is 100% with one parameter 'key' described as 'Key of the field to remove.' The description does not add additional semantic information beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states it removes a custom field definition by key and clarifies that existing values are retained but hidden. This distinguishes it from sibling tools like add_crm_field or list_crm_fields.

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 removing custom fields but does not explicitly specify when to use or not use this tool versus alternatives or provide any exclusion criteria.

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 already indicate destructiveHint=true and idempotentHint=true. The description adds context: leads are moved automatically and there's a restriction on deleting the last stage. No contradiction.

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

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

Two sentences with no wasted words. Critical information is front-loaded.

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

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

Given the simple schema and annotations, the description covers core behavior, constraints, and parameter semantics. It is sufficient for the tool's complexity.

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

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

Schema coverage is 100%, but the description adds meaning for reassign_to by stating the default fallback (first remaining stage). This helps the agent understand optional behavior.

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 (Delete), the resource (pipeline stage), and the method (by key). It directly distinguishes from sibling tools like add_crm_stage, rename_crm_stage, and list_crm_stages.

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 what happens to leads (moved to reassign_to or first remaining stage) and states a constraint (can't delete last stage). It could mention alternatives like rename_crm_stage but provides clear usage context.

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

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

The description adds behavioral context beyond annotations: it scrapes profile URLs, saves data onto contacts, merges into profile_data, and notes that each contact is a real LinkedIn profile view. Annotations already indicate idempotentHint and openWorldHint, which align. No contradiction.

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, with key information front-loaded. Every sentence adds value, no fluff.

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 still mentions returns per-contact enrichment status. It covers purpose, usage, constraints, and behavioral traits comprehensively.

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

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

Schema coverage is 100%, but the description adds that profile_id is optional and defaults to active profile, and reinforces the max 8 limit for contact_ids. This adds value beyond the schema definitions.

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

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

The description clearly states that the tool enriches contacts with LinkedIn profile data, listing specific fields (headline, location, current company & position, experience, education, skills). It distinguishes from sibling tools like search_google_xray and connect_linkedin by context.

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

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

The description explicitly says to use after search_google_xray to flesh out leads and warns about batch size (max 8 per call). It provides clear context but doesn't mention specific situations where the tool should not be used.

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 already indicate read-only, idempotent, non-destructive. Description adds that it returns CSV text, up to limit rows, and suggests alternative for large DB, which is helpful behavioral context beyond annotations.

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

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

Two sentences: first defines purpose and output, second gives usage guidance. No wasted words, front-loaded with key 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?

No output schema, but description explains return type (CSV text). Parameter is fully documented. Includes limitation note. Complete for a simple export 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?

Single parameter 'limit' is described in schema (100% coverage). Description repeats 'returns up to limit rows' but doesn't add new semantic meaning beyond what's in 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 'export CRM to CSV text', specifies content (leads with pipeline stage and key fields) and format. Distinct from sibling tools like list_crm_fields or add_crm_stage.

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 limit info and advises using in-app button for very large databases. Gives clear when-to-use context but could be more explicit about not using for bulk operations.

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

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

The description discloses that the message is stored as a draft with status 'pending_approval' and is not sent. This adds value beyond the annotations, which only indicate the tool is not read-only. It does not mention overwrite behavior on regeneration, but the overall behavior is well explained.

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

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

The description is two sentences, front-loading the core action and then clarifying the non-sending aspect and workflow. Every sentence adds value with no redundancy.

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

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

Given the tool's complexity (3 parameters, no output schema), the description adequately covers purpose, workflow, and key behavioral details. It does not mention prerequisites or return values, but those are not critical for a draft-generation tool with clear annotations.

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 100% schema coverage, the baseline is 3. The description adds context by explaining how custom_instructions are appended to the step's ai_prompt, and it maps the required parameters to the campaign_contact and step. This justifies a score above baseline.

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 or regenerates an AI personalized message draft for a specific campaign_contact and step. It uses specific verbs and resources, and distinguishes itself from sibling tools like approve_message and list_pending_approvals by explicitly defining its role in the workflow.

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

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

The description tells when to use the tool: to generate a draft that is not sent and waits for review. It also explicitly guides the user to use list_pending_approvals and approve_message to release the draft, providing clear alternatives and workflow context.

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

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

Annotations already indicate read-only, idempotent, non-destructive. Description adds real-time behavior, message ordering, and the presence of 'is_sender' field in responses, which is beyond annotations.

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

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

Three concise sentences with clear front-loading of purpose. No unnecessary words.

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

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

No output schema, but description hints at response fields (is_sender) and real-time behavior. Sibling context establishes it as a read tool before replying. Slightly lacking details on pagination through cursor.

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

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

Schema covers all parameters with descriptions (100% coverage). Description adds no extra parameter details, though it mentions a response field (is_sender) which is helpful for understanding output.

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

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

Clearly states the tool reads messages of a single LinkedIn conversation in real time, with newest last order. Distinguishes from siblings like list_inbox_chats and reply_to_chat.

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 directs to get chat_id from list_inbox_chats and use messages to understand context before replying with reply_to_chat. Provides clear context but no explicit when-not 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?

Annotations already declare readOnlyHint and destructiveHint, so the description adds value by specifying the exact fields returned, including the Czech vocative, without contradicting annotations.

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

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

Two sentences with no wasted words; front-loaded with the primary purpose and then lists what it returns and when to use it.

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

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

Given the simple input schema (one param) and no output schema, the description adequately explains the return value and use case, leaving no significant gaps.

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

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

Schema coverage is 100% (single required parameter with description), and the description does not add additional semantics beyond what the schema already provides for the parameter.

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

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

The description clearly states the tool returns a full contact profile and lists specific fields (name, headline, company, etc.), distinguishing it from sibling tools like list_contacts or get_lead_context.

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

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

The description explicitly indicates the tool is for providing context for personalized messages or next-step decisions, but does not include when not to use it or mention alternatives.

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

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

The description adds context beyond annotations: returns specific fields, optional profile behavior, and error response formatting. Annotations already declare readOnlyHint and idempotentHint, and the description aligns with them.

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

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

The description is two sentences long, front-loaded with the main purpose, and every word adds value. No unnecessary repetition.

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

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

Given the tool's simplicity (one optional param, no output schema), the description covers all behavioral aspects: what it returns, defaulting logic, error handling. Annotations provide the safety profile.

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 profile_id is described in the schema, but the description adds significant detail: defaulting behavior, 'first' profile logic, and error listing all profiles. This enhances understanding 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 tool checks remaining daily quota for a profile, listing specific returned information (usage vs limits, ramp-up status, allowed hours). It is distinct from sibling tools, none of which perform this function.

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 the optional profile_id parameter, defaulting to active profile, and error behavior if no profile exists. It does not explicitly mention when to use this tool versus alternatives, but the context of sibling tools makes this 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds behavioral context by enumerating the extensive data fetched (conversation summaries, tasks, interactions, stage history), which goes beyond annotations without contradiction.

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

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

Single sentence front-loads purpose, then lists fetched items. Slightly list-heavy but efficient and clear, with no extraneous 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?

Despite lacking an output schema, the description thoroughly enumerates return categories (profile, stage, fields, messages, summaries, tasks, interactions, history), providing complete context for an agent to understand what data is returned.

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

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

Schema coverage is 100% and the description does not add additional parameter-level details. Baseline 3 is appropriate as the schema already documents both parameters with 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?

Description clearly states the tool fetches full CRM context for a lead, listing specific components (profile, pipeline stage, custom fields, etc.) and distinguishes it from siblings like get_contact_profile and list_lead_messages by being comprehensive.

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 advises 'Call this first for highly personalized outreach' and provides context: before writing a pitch or follow-up. Does not explicitly list when not to use, but the specific sibling tools imply alternatives for narrower tasks.

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 declare readOnlyHint, idempotentHint, destructiveHint. Description adds that it returns connection state and fix instructions, plus default profile_id behavior. No contradictions. Provides useful behavioral context beyond annotations.

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

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

Two sentences covering purpose, return value, and usage context plus a separate sentence for parameter. Front-loaded with primary action. No unnecessary words.

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

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

For a simple status check tool with no output schema, the description fully explains what is returned (connection state and fix info) and when to use it. Parameter default is specified. Complete for agent 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?

Only one optional parameter (profile_id). Schema description exists, but tool description adds that it defaults to the active/first profile, which is valuable for agent invocation.

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 checks LinkedIn account connection status, returns state and fix instructions, and specifies when to call it (upon account errors). It distinguishes from sibling 'connect_linkedin' by focusing on status checking.

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?

Explicit guidance to call this first when encountering ACCOUNT_NOT_CONNECTED or ACCOUNT_BLOCKED errors. No explicit when not to use, but the context of error codes implies purpose. Could be improved with alternative tool mentions.

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 already indicate readOnlyHint=true and destructiveHint=false. The description adds details about filtering by status and the exact fields returned, providing full transparency beyond the annotations.

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

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

Two concise sentences. First lists output fields, second states usage purpose. No fluff, front-loaded with key 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?

For a simple list-with-filter tool, the description fully covers purpose, parameters, and return fields. No output schema needed given the explicit field list in the description.

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

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

Schema coverage is 100% for the single optional parameter 'status' which is an enum. The description only says 'Filter by campaign status. Optional.' which adds no extra semantics beyond the schema's enum values.

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

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

The description clearly states the tool lists campaigns with specific fields (ID, name, status, description, lead counts), and explicitly mentions its purpose for obtaining campaign_id for subsequent operations like adding leads or generating messages.

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 context: 'Use this to obtain campaign_id when adding leads, generating messages or approving drafts.' This tells the agent when to invoke this tool versus 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. Description adds return field details and workflow context, providing value beyond annotations without contradiction.

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

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

Two sentences, front-loaded with core action and return fields, no filler. Every word adds value.

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

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

Given high schema coverage and informative annotations, the description sufficiently explains the tool's purpose, output fields, and integration in the toolset, compensating for lack of output schema.

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

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

Schema covers all parameters (100% coverage) with clear descriptions. The description does not add new parameter semantics beyond the schema, maintaining the baseline.

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

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

The description clearly states the tool lists contacts in a specific lead list, enumerates the fields returned, and mentions its role in providing IDs for further tools, distinguishing it from siblings like enrich_contacts.

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?

Description implies usage as a precursor to tools requiring contact IDs ('The AI picks IDs from this list for further tools'), but does not explicitly specify when not to use or name 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?

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds no behavioral traits beyond confirming the read operation. No contradiction, but no extra value.

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

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

Single sentence with front-loaded verb and resource. No wasted words, clearly conveys purpose and a hint of usage.

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 parameterless list tool, the description covers what is returned (key, label, type) and mentions the companion tool set_lead_fields. Sufficient given no output schema.

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

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

No parameters exist, so schema coverage is 100%. Baseline for 0 parameters is 4, and the description does not need to add parameter info.

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 action (List), the resource (custom fields on CRM leads), and the returned data (key, label, type). It clearly distinguishes from siblings like add_crm_field and set_lead_fields.

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 listing fields before setting them with set_lead_fields, but lacks explicit when-to-use or when-not-to-use guidance compared to 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by specifying exact output fields (key, label, order, color, lead counts) and noting that stages are user-configurable, providing additional context beyond the safety annotations.

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

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

Two sentences, no wasted words. The first sentence lists output fields; the second provides usage guidance referencing sibling tools. Information is front-loaded and every sentence earns its place.

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

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

Given the tool's simplicity (no parameters, no output schema), the description is complete. It covers output fields, the fact that stages are configurable, and directs to sibling tools for modifications. Annotations and context signals are rich.

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

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

The input schema has zero parameters with 100% schema coverage (trivially). Since there are no parameters, the description does not need to add parameter semantics but still clarifies the tool's output, which is sufficient. Baseline score of 4 is appropriate.

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

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

The description explicitly states the tool lists CRM pipeline stages along with key attributes (key, label, order, color) and lead counts. It uses a clear verb ('List') and resource ('CRM pipeline stages'), and distinguishes from sibling modification tools (add_crm_stage, etc.).

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

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

The description provides clear guidance on when to use this tool (to view stages and lead counts) and explicitly directs agents to use other sibling tools for modifications: 'rename/add/delete them with the other crm_stage tools.'

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 already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds behavioral traits: 'in real time,' return fields (chat_id, provider id, unread count, last-message timestamp), and the caveat about message preview not always being provided. This enriches the agent's understanding beyond annotations without contradiction.

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 at three sentences, front-loading the core purpose. Every sentence provides necessary information: the action, return fields, a limitation, and an optional parameter default. No superfluous content.

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 three parameters, no output schema, and supportive annotations, the description fully covers what an agent needs: return fields, limitation on preview text, and how to get full messages using a sibling tool. It is complete for effective 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?

The input schema has 100% coverage with descriptions for all three parameters. The description adds only minimal value: it restates that profile_id is optional and defaults to active profile (already in schema) and implies pagination context for cursor. It does not explain the limit range or provide new information, so baseline 3 is appropriate.

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

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

The description clearly states 'List recent LinkedIn inbox conversations (chats) in real time,' specifying both the action (list) and the resource (inbox chats). It distinguishes itself from sibling tools like get_chat_messages and reply_to_chat by referencing them, making the purpose unambiguous.

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

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

The description advises when to use get_chat_messages instead ('Message preview text is not always provided... call get_chat_messages to read the actual messages'), providing clear alternatives. It also notes that profile_id is optional and defaults to the active profile, giving contextual usage guidance. However, it does not explicitly state when not to use this tool.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds ordering behavior 'newest first' and the fact that messages are stored drafts. However, it does not disclose pagination defaults or behavior when no messages exist.

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

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

Two sentences, front-loaded with action and ordering. No redundant words; the second sentence adds optional filtering and use case. Optimal length.

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

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

The description explains what is listed (messages by channel and kind) and the use case. No output schema exists, but the description implies a list of message copies. Lacks mention of pagination or field details, but is sufficient for a read-only list 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 description coverage is 100%; all parameters are documented in the input schema. The description reiterates filtering by channel or kind but does not add new semantic meaning beyond what the schema provides.

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

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

The description explicitly states the verb 'List', the resource 'stored outreach messages saved on a CRM lead', and the ordering 'newest first'. It clearly distinguishes from sibling tools like list_inbox_chats by specifying CRM-lead-scoped saved messages.

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

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

The description provides a concrete use case: 'Use to pull the copy back out of the CRM before sending it via the right channel.' It mentions optional filtering, but lacks explicit guidance on when not to use or specific 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that it returns specific fields and is for bulk review, which aligns with annotations and provides additional 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?

Two sentences, front-loaded with the main purpose. Every sentence adds value without redundancy.

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

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

Given no output schema, the description specifies the fields returned and the usage context (input for bulk review). It is complete for a read-only list 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 100% and describes limit and campaign_id. The description reiterates the optional filter but does not add new semantic 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 tool returns AI drafts pending approval with specific fields (contact name, headline, company, generated text). It distinguishes from siblings like approve_message and reject_message by being the read-only list tool.

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 indicates the tool is used as input for bulk review by an AI assistant to iterate through drafts and approve/reject them. It does not explicitly mention when not to use, but the context is 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?

Annotations already indicate read-only and safe operation. Description adds behavioral details like filter options and returned fields (id, title, due date, status, linked lead's name), which is useful beyond annotations.

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

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

Two sentences, no wasted words. Front-loaded with the core purpose. Highly 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?

Despite no output schema, the description states exactly what is returned. Given the tool's simplicity (3 optional params, list operation), the description is fully complete.

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

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

Schema coverage is 100%, so baseline is 3. Description mentions filtering by status and contact but doesn't add meaning beyond what the schema already provides (e.g., default status 'open'). No extra parameter elaboration.

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 your CRM tasks' with a specific verb and resource. It distinguishes from sibling tools like complete_task and create_task by listing tasks rather than modifying them.

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

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

Provides context on when to use: 'Use to see what follow-ups are outstanding.' While it doesn't explicitly state when not to use or name alternatives, the context is clear enough.

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 already indicate readOnlyHint=false and destructiveHint=false. The description adds context about storing structured data separately, but does not disclose side effects, permissions, or idempotency. It adds some value by describing what the tool stores, but behavioral details are limited.

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 (3 sentences), front-loaded with the primary purpose, and contains no unnecessary words. Every sentence adds value.

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

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

Given the tool's simplicity (4 parameters, no output schema), the description covers the essential aspects: what it does, what to provide, and how it differs from raw message storage. It is sufficiently complete for an AI 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?

Schema coverage is 100%, so baseline is 3. The description mentions summary, pain points, and sentiment, but adds minimal additional meaning beyond the schema descriptions. It does not elaborate on formats or constraints.

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

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

The description clearly states the tool's purpose: 'Save a structured summary of a conversation into the CRM for a lead.' It specifies the verb (save), resource (CRM note for a lead), and content (summary, pain points, sentiment). This distinguishes it from sibling tools like save_lead_message, which saves raw message history.

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 guidance on when to use: 'Analyze the chat/context yourself, then call this with a concise summary...' It also differentiates from alternatives by noting 'Stored separately from raw LinkedIn message history.' However, it does not explicitly state when not to use the 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?

Annotations show readOnlyHint=false, destructiveHint=false, idempotentHint=true, and the description adds valuable context about preventing re-surfacing. The description aligns with annotations and adds behavioral insight beyond them.

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

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

A single, front-loaded sentence that conveys the purpose and usage. Every word earns its place, with no waste.

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

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

For a simple, one-action tool, the description is complete. It explains the utility and outcome, requires no output schema, and is sufficient for an AI 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?

Schema coverage is 100%, so the description doesn't need to explain parameters. It mentions 'by chat_id' but doesn't elaborate on the optional profile_id. Baseline 3 is appropriate as schema does the heavy lifting.

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 (mark as read) and the resource (LinkedIn conversation by chat_id). It distinguishes from siblings like reply_to_chat or get_chat_messages by specifying the exact purpose and context.

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

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

The description explicitly says 'Useful after the AI has processed/answered a thread so it does not re-surface as unread,' providing clear when-to-use guidance. It lacks explicit when-not-to-use or alternative tools, but the context is sufficient for a simple 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?

The description adds key behavioral context beyond annotations: the anti-detection delay (30-180s), the interaction between auto_publish and approval settings, and the lack of attachment support. Annotations indicate readOnlyHint=false and destructiveHint=false, which are consistent with a creation tool. The description does not cover error handling or account status checks, but provides sufficient transparency.

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

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

The description is concise and front-loaded with the main action. It covers key nuances (draft, auto_publish, delay, attachments) in three dense sentences 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?

Given the tool has no output schema, the description adequately covers input behavior, draft/publishing, approval interaction, and limitations. It does not detail error cases or rate limits beyond the anti-detection delay, but these are not critical for basic usage.

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?

All 5 parameters have schema descriptions (100% coverage), so baseline is 3. The description adds value by explaining the default for auto_publish, the LinkedIn Markdown limitation for text, the required UUID format for profile_id, and the admin requirement for as_organization. This goes 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 tool creates a LinkedIn post for a connected profile, specifying the verb 'Create' and the resource 'LinkedIn post'. It distinguishes from sibling tools by focusing on LinkedIn-specific actions and publishing behavior.

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 the default draft behavior and the auto_publish option, including how it respects the MCP human-in-the-loop setting. It also notes that attachments are not supported via MCP, guiding usage. However, it does not explicitly compare to sibling tools like send_linkedin_message.

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 show readOnlyHint=false (mutation), idempotentHint=true, destructiveHint=false. The description adds that it resets generation_status to 'pending' and triggers regeneration, which is transparent about the state change. No contradictions with annotations.

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

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

The description is two sentences long, front-loaded with the action and key impact. Every sentence provides essential information with no wasted words.

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

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

For a simple mutation tool with no output schema, the description adequately covers purpose, effect, and parameter roles. It could mention preconditions (e.g., that drafts must exist) but overall is complete enough for an AI 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?

Schema has 100% coverage on 2 parameters, so baseline is 3. The description adds value by stating that the 'reason' parameter is used as regeneration feedback and that 'campaign_contact_id' identifies the contact. This contextualizes the parameters beyond their 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 it rejects drafts on a campaign_contact with textual feedback. The verb 'Reject' and resource 'current drafts' are specific, and it distinguishes from sibling tools like 'approve_message' which likely does the opposite.

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 the tool (when rejecting drafts with feedback) and the consequence (resets generation_status to pending for regeneration). It implies not to use when approving, but doesn't explicitly state when-not or list alternatives beyond the implicit contrast.

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?

Description adds that the stage key and leads are unchanged, complementing annotations (idempotentHint=true, destructiveHint=false). No contradictions.

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

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

Two concise sentences, front-loaded with purpose and dependency information. No unnecessary words.

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

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

For a simple rename operation with annotations, the description sufficiently covers behavior and parameters. No output schema needed; return values are implied.

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 already covers all 3 parameters with descriptions (100% coverage). Description adds minimal extra insight for 'key' (usage hint), but not substantial for 'color' or 'label'.

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 action: rename a stage's label and/or change its color. It specifies the resource (CRM stage) and the method (by key), distinguishing it from sibling tools like add_crm_stage or delete_crm_stage.

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 a helpful pointer to use list_crm_stages to get keys. Does not explicitly say when not to use, but given the sibling tools, usage context is clear enough.

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

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

The description claims an idempotency guard prevents double-sends, implying the tool is idempotent, but the annotation 'idempotentHint' is false, creating a direct contradiction. According to rules, a score of 1 is required when the description contradicts annotations.

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

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

The description is relatively long but all sentences add value. It front-loads the main purpose and then provides ordered details. Could be slightly more concise, but structure is logical.

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 many behavioral aspects (hours, HITL, scanning, rate limits) but lacks description of the success return value or output format. Since no output schema exists, the description should compensate. The omission of success response details makes it slightly incomplete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds useful context: chat_id comes from list_inbox_chats, message max 5000 chars, profile_id is optional. This extra information justifies a score above baseline.

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 sends a reply into an existing LinkedIn conversation by chat_id. It specifies the verb and resource but does not explicitly differentiate from the sibling 'send_linkedin_message' which might be for new messages. This slight ambiguity prevents a perfect score.

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 when-to-use and when-not-to-use guidance: allowed hours, HITL approval, idempotency, URL scanning, and rate limits. It explains behaviors in different conditions (outside hours, scan trip), giving clear 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?

The description discloses behavioral traits beyond annotations: it emphasizes the CRM acts as a 'sponge' for durable context, clarifies the lifecycle (draft to queued to sent), and explicitly states that the tool does not send anything. All annotations are consistent (readOnlyHint false, no contradictions).

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

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

The description is concise yet comprehensive. It uses bullet-like formatting (dashes), front-loads the primary purpose, and every sentence adds meaningful guidance. There is no redundancy or wasted words.

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

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

For a storage tool with no output schema, the description fully explains the tool's role in the larger workflow: saving messages for later retrieval via get_lead_context/list_lead_messages, and pushing to channels via their own tools. It covers the lifecycle, update mechanism, and integration with sibling tools, making it contextually complete.

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

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

Schema description coverage is 100%, so each parameter has its own description. The tool description adds workflow context (e.g., 'set status to sent after you push it elsewhere') and explains defaults (kind: 'initial', status: 'draft', channel: 'email'). This provides added value beyond the schema alone, justifying a slightly higher score.

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

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

The description clearly identifies the tool's purpose: storing generated outreach messages on a CRM lead. It uses specific verbs like 'Store', 'save', and explicitly distinguishes from sending by stating 'Does NOT send anything'. It also references related sibling tools (get_lead_context, list_lead_messages) to provide context.

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 guidance on when to use the tool: to save copy that will later be read and pushed via channel tools. It explains when not to use it (not for sending) and mentions alternatives like Smartlead for email. It also gives instructions for updating existing messages using message_id.

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 indicate read-only, idempotent, non-destructive. The description adds behavioral details: returns truncated plain text, emails_found, treats content as untrusted data, rate limits, and refuses private/internal addresses. This complements annotations well without contradiction.

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?

Three concise sentences. The first sentence states purpose and use case, the second describes return values, the third covers important restrictions. No fluff.

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 adequately explains return values (plain text, emails) and limitations (truncation, rate limits, security warning). Together with annotations, this provides a complete picture for an agent.

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

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

Schema description coverage is 100%, so the schema already documents both parameters (url and max_chars). The description adds no further parameter-specific details beyond the schema. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool fetches readable text of a public web page and specifies the use case (reading a prospect's website or article). It distinctly separates from sibling tools which are CRM and messaging focused.

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

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

The description provides clear context for when to use (fetching public web pages for context) and notes restrictions (rate-limited, private addresses refused). It does not explicitly state when not to use or list alternatives, but given no sibling scraping tool exists, this is sufficient.

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

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

The description discloses all important behaviors: saves profiles into a specific list, deduplicates by URL, paginates, auto-filters duplicates, returns contact_id values. Annotations (nondestructive, not read-only) are consistent; no contradictions.

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

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

Three concise sentences, front-loaded with purpose and key behavior, followed by usage tips. Every sentence adds value without redundancy.

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

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

Covers purpose, usage, side effects, return values, and integration with other tools. For a 5-parameter search tool without output schema, this is complete and well-rounded.

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

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

Schema coverage is 100%, so the description does not need to detail each parameter. However, it adds minimal value beyond the schema—only implied context about Google operators. Adequate but no extra semantic richness.

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 performs a Google X-Ray search for public LinkedIn profiles using Google operators, distinguishing it from sibling LinkedIn-native search tools. It specifies the resource (LinkedIn profiles) and the method (site:linkedin.com/in operators).

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?

Explicit guidance: useful when avoiding LinkedIn search limits; explains that results are saved to contacts and returns contact IDs; advises using add_contacts_to_campaign or set_deal_stage for CRM actions. This clearly indicates when and why to use this tool versus 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?

Beyond annotations (readOnlyHint false, indicating mutation), the description discloses that leads are saved into contacts and IDs returned, providing clear behavioral context. It does not mention potential errors or side effects, but adds value over annotations.

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

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

The description is a single sentence, front-loading the core action and outcome with no redundant words. It is appropriately concise for a straightforward tool.

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

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

Given the lack of output schema, the description explains the main side effect (saving contacts) and return (IDs). It could mention URL format requirements or error handling, but for a simple scraping tool with two parameters it is largely 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?

With schema coverage at 100%, the description reinforces that 'search_url' should be a ready-made URL with filters, adding nuance beyond the schema description. The 'limit' parameter is explained in the schema; the description adds no further value for it.

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 scrapes a Sales Navigator or standard LinkedIn search URL, specifying the input (ready-made URL) and output (saved contacts with IDs). It distinguishes from sibling 'search_linkedin_people' which likely builds a search rather than using a pre-built URL.

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 indicates to use this tool when you have a pre-filtered search URL, implying an alternative for parameter-based searching. However, it does not explicitly state when not to use it or name specific alternatives beyond the sibling list.

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 (openWorldHint: true) indicate side effects, and the description adds crucial detail: results are saved directly into contacts with deduplication and blacklist filtering, and it returns IDs for use in other tools. This goes beyond what annotations alone provide.

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

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

The description is three sentences, front-loaded with the main purpose and side effects, then param details. It is concise without sacrificing key information, earning its sentences.

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

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

Given the tool's complexity (5 params, no output schema, side effects), the description covers the core behavior, side effects (saving contacts), and param guidance. It could mention the return type more explicitly, but the reference to 'IDs that the AI uses in other tools' is sufficient for an agent.

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

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

Schema coverage is 100%, so default baseline is 3. The description adds value by explaining the difference between 'location' (human-readable) and 'locationId' (raw ID), and clarifies that results are saved and return IDs, which aids in understanding the tool's integration.

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 'Search people on LinkedIn by keywords, title, location or company', which is a specific verb+resource. However, it does not distinguish from the sibling tool 'search_linkedin_navigator', which likely has a similar purpose.

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

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

The description implies usage for searching people and saving contacts, but provides no explicit guidance on when to use this versus alternatives like 'search_google_xray' or 'search_linkedin_navigator'. It only clarifies param usage for location/locationId.

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 key behavioral traits beyond annotations: message always empty regardless of account type, enforces daily limits, allowed hours, blacklist, random delays, and usage tracking. No contradiction with annotations.

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

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

Two efficient sentences, front-loaded with the primary action, no wasted words.

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

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

Given no output schema, the description fully covers the tool's behavior and constraints, making it complete for an agent to understand invocation requirements.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds that contact_id is for blacklist check but does not provide significant extra 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 verb 'Send' and the resource 'LinkedIn connection invitation', and distinguishes it from siblings like send_linkedin_message by specifying the message is always empty.

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 context on when to use (connection requests) and constraints (empty message, daily limits, hours, blacklist, delays). However, does not explicitly state when not to use or mention alternatives.

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

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

Discloses random delay (30-180s) for anti-detection, daily message limit counting, allowed hours respect, and logging, which goes well beyond the annotations (readOnlyHint=false, etc.) with actionable behavioral traits.

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

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

Two sentences front-load the primary action and then add key behavioral details. No wasted words.

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

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

Provides adequate context for a send operation without output schema: covers anti-detection, limits, logging. Slightly lacking on success/error feedback but acceptable given annotations.

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

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

Schema coverage is 100% with descriptions for all three parameters. The description adds no additional parameter details beyond the schema, so baseline 3 is appropriate.

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

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

Description uses specific verb 'Send' and resource 'one-off LinkedIn message to a specific contact', clearly distinguishing from campaign messages mentioned in sibling tools.

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

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

States it is for messages 'outside any campaign' and includes behavioral constraints (delay, daily limit, allowed hours), but does not explicitly mention when not to use or name alternatives like generate_campaign_message.

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

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

Beyond annotations (idempotent, non-destructive), description adds that it logs the changer and optional note to deal history, providing useful side-effect 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?

Three short sentences, front-loaded with action, then usage guidance, then side effects. No wasted words.

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

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

Fully covers what the tool does, when to use, parameter hints, and behavioral consequences. Absence of output schema is acceptable for a mutation 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 100% with good descriptions already. The tool description largely repeats schema info (stage defaults, optional note) without adding new meaning.

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

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

The description uses a specific verb 'Move' and resource 'lead to a different pipeline stage', clearly distinguishing it from sibling tools like list_crm_stages or add_crm_stage.

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 states when to call: 'when the user confirms a real-world event' with examples, and directs to list_crm_stages for valid keys.

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 provide idempotentHint=true and non-destructive hint. The description adds valuable behavioral context: 'Adds the lead to the CRM if needed' and 'Only defined field keys are accepted', which goes beyond the annotations and helps the agent understand side effects and constraints.

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 concise: two sentences that cover purpose, parameter format, key constraint, and side effect. No wasted words; every sentence earns its place.

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

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

Given the tool's complexity (nested object, no output schema), the description covers the main behaviors: how to use, key constraints, and lead creation. It could mention return value or error handling, but overall it is sufficiently complete for a write operation with idempotent annotations.

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

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

The schema covers 100% of parameters with descriptions, but the description adds crucial meaning: 'fields' must contain only predefined keys (from list_crm_fields) and contact_id is a UUID. This constraint prevents invalid inputs and improves understanding.

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

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

The description clearly states the verb 'Set' and resource 'custom field values on a lead', specifies the required parameter format (contact_id, fields object), and distinguishes from sibling tools like update_contact by focusing on custom fields and lead creation side effect.

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

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

The description provides clear context for when to use (to set custom field values) and references list_crm_fields to check valid keys. However, it does not explicitly state when not to use or list alternatives, though the sibling set implies this is the correct tool for the job.

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

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

Beyond the annotations (idempotentHint, destructiveHint), the description reveals that execution respects daily limits, allowed hours, and anti-detection delays, which are important behavioral details not captured in structured fields. However, it does not clarify behavior if the campaign is already running (though idempotentHint suggests it is safe to call again).

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

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

The description is two concise sentences: the first states the core action and its effects, the second adds prerequisites and behavioral constraints. No filler or redundancy; every sentence earns its place.

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

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

Given the tool's simplicity (one parameter, no output schema) and the presence of complete annotations, the description covers the essential aspects. It lacks an explicit mention of the return value or success indicator, but this is a minor gap for a mutation tool in a broader system.

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

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

The input schema has 100% description coverage for campaign_id ('UUID of the campaign to start'), so the description adds no further parameter meaning. This meets the baseline for high schema coverage.

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

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

The description clearly states the verb 'Start (activate)' and the resource 'existing campaign', and details the effects: scheduling outreach actions and setting status to 'running'. This distinguishes it from siblings like create_campaign (creation) and stop_campaign (deactivation).

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

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

The description explicitly notes prerequisites: the campaign must already have contacts (from add_contacts_to_campaign) and steps, which guides the agent on proper workflow ordering. However, it does not explicitly state when not to use this tool (e.g., if the campaign is already running) or name 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 pending scheduled actions are cancelled (via a DB trigger), which is beyond the annotations. Annotations indicate destructive and idempotent, consistent with description.

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

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

Two sentences, front-loaded with the core action. No redundant words, every sentence adds value.

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

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

Complete for a simple tool with one required parameter and no output schema. Explains effect, side effects, and alternative.

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?

Only one parameter 'campaign_id' with schema description already clear. The description adds no further parameter details beyond what the schema provides.

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

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

The description clearly states the tool stops a running campaign by setting status to 'stopped' and cancelling pending scheduled actions. It distinguishes from the sibling 'update_campaign_settings' which is for pausing.

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 guidance on when to use this tool (to stop) versus the alternative 'update_campaign_settings' for pausing. This prevents misuse.

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 already indicate idempotency (idempotentHint=true) and non-destructiveness (destructiveHint=false). The description adds value by specifying that only provided fields are changed (partial update) and implying ownership requirement. This enhances transparency beyond annotations, though it does not detail other behavioral aspects like authorization 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 concise, using only three sentences with no filler. It front-loads the key purpose and immediately lists the modifiable fields, then provides usage nuance for status, and ends with the important note on partial updates. Each sentence earns its place.

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

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

Given the lack of an output schema and the tool's moderate complexity (7 optional parameters, destructive=false, idempotent=true), the description covers the essential aspects: what settings can be updated, how to use status, and that updates are partial. It does not mention prerequisites (e.g., campaign existence) or error conditions, but those are implicitly understood. The description is fairly complete for a straightforward update 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?

The input schema has 100% coverage with individual parameter descriptions. The description merely lists the fields and adds minimal extra value by explaining how to use status for pausing/resuming. Since the schema already describes each parameter, the description does not significantly deepen semantic understanding 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 specifies the verb 'Update' and the resource 'settings of an existing campaign', listing the specific fields modifiable. It distinguishes this tool from sibling tools like create_campaign (creation) and start_campaign/stop_campaign (focused on status changes) by covering a broader set of settings, including status. The description is specific and not 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?

The description provides clear context: it is for updating settings of a campaign the user owns, and it explains that only provided fields are changed. It gives explicit guidance on using status values to pause or resume. However, it does not explicitly direct the user to use alternative tools (like start_campaign/stop_campaign) for simpler status changes, nor does it state when not to use this tool.

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

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

Annotations already indicate idempotent and non-destructive behavior. Description adds that only passed fields are changed, reinforcing partial updates and no side effects beyond specified fields.

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

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

Two sentences covering purpose, usage, and behavior with no unnecessary words. Highly front-loaded.

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

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

Tool is simple with 7 params, no output schema. Description covers purpose, usage, and constraints. Could mention return value, but not essential given no output schema.

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

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

Schema coverage is 100% with good descriptions. Description adds meaning by explaining partial update semantics and listing key fields. Does not duplicate schema 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?

Clearly states 'Update a lead's contact details' and lists specific fields. Distinguished from sibling tools like 'set_lead_fields' which is more generic, and 'enrich_contacts' which enriches via external data.

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 a use case ('save an email address you found'), explains partial updates, and explicitly states it does not create contacts. Clearly sets context but does not name alternative tools.

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