Server Quality Checklist

Tool Scores

• sf_campaign_membersA
  4/5.0
  Behavior4/5

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

  Annotations already indicate readOnlyHint=true and destructiveHint=false. Description adds that it returns member name, type, status, response date, and explicitly marks [READ-ONLY], reinforcing safe read behavior.

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

  Conciseness3/5

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

  The description is somewhat redundant, repeating similar information in two sentences. The '[INSTRUCTIONS]' prefix is unnecessary. Could be more compact and focused.

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

  Completeness4/5

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

  No output schema, so description covers return fields (member name, type, status, response date). Lacks details on error handling or edge cases, but for a simple read tool with 2 params, it is reasonably complete.

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

  Parameters3/5

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

  Schema coverage is 100%, with descriptions for campaignId and limit. The description mentions campaign in context but adds no new parameter details beyond schema. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states it retrieves CampaignMember junction records for a campaign, listing specific fields. It distinguishes from siblings like sf_add_campaign_member (adds) and sf_campaign_performance (performance).

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

  Usage Guidelines4/5

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

  Provides specific use cases: 'see who is in a campaign, track engagement, or analyze campaign reach'. Implicitly advises against using for adding or performance analysis. Could explicitly mention alternatives but clear enough.

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

• sf_search_campaignsA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true. Description reinforces with '[READ-ONLY]' and describes return payload, adding value 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.

  Conciseness3/5

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

  Description is somewhat verbose with a list of fields, but structured with instructions and read-only tag. Could be more concise.

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

  Completeness4/5

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

  Given 2 params and no output schema, description covers purpose, usage, and return values adequately. Missing mention of default limit (20) but schema handles that.

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

  Parameters3/5

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

  Schema coverage is 100%, so params are fully documented. Description adds minimal extra meaning, only reiterating 'name keyword'. Baseline 3 applies.

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

  Purpose5/5

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

  The description clearly states it queries the Campaign sObject and lists specific returned fields (name, status, type, dates, metrics). It distinguishes from siblings by being a search-by-name tool.

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

  Usage Guidelines4/5

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

  Explicitly states when to use: 'when the user asks about marketing initiatives, campaign performance, or budget spend.' Provides read-only context but lacks explicit 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.

• sf_campaigns_by_statusA
  4.2/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is safe. The description reinforces this with '[READ-ONLY]' and adds behavioral context by listing the specific metrics returned (lead/contact counts, budget, conversion data), which goes 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.

  Conciseness4/5

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

  The description is concise with two main sentences and an initial instructions line that may be redundant. It front-loads the key information. Despite the slight redundancy, it earns a 4 for efficiency.

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

  Completeness5/5

  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 the return data (campaigns with lead/contact counts, budget, conversion data). For a simple 2-param tool with good annotations, this is fully complete.

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

  Parameters3/5

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

  Schema coverage is 100% with both parameters described. The description essentially repeats the status values (Planned, In Progress, Completed, Aborted) and does not add extra meaning beyond the schema. No details on the limit parameter are added. Baseline 3 is appropriate.

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

  Purpose5/5

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

  The description clearly states the verb 'Filters Campaign records by Status' and specifies the resource (campaigns) and the primary filter. It also mentions the returned data (lead/contact counts, budget, conversion data) and provides example queries. This distinguishes it from siblings like sf_search_campaigns and sf_campaign_performance.

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

  Usage Guidelines4/5

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

  The description gives example use cases ('which campaigns are currently running?', 'show completed campaigns with their results') which guide when to use the tool. However, it does not explicitly exclude alternatives or state when not to use it, missing some comparative guidance.

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

• sf_add_campaign_memberA
  4.3/5.0
  Behavior4/5

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

  Annotations only show destructiveHint: false. Description discloses it creates a non-destructive record, returns the created membership, and mentions status defaults. No hidden side effects; adds 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.

  Conciseness4/5

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

  Two paragraphs: first with instructions, second a summary. Front-loaded with purpose. Some redundancy (e.g., 'Add a lead or contact...' echoes first sentence), but generally efficient.

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

  Completeness4/5

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

  No output schema, but description mentions return value. Covers key aspects: what it does, parameter constraints, status options. Lacks error handling or prerequisite info (e.g., campaign must exist), but adequate for a simple create tool.

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

  Parameters4/5

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

  Schema coverage is 100% (baseline 3). Description adds mutual exclusivity of contactId/leadId, default status, and possible status values, enhancing understanding beyond the schema alone.

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

  Purpose5/5

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

  The description clearly states it creates a CampaignMember junction record linking a Lead or Contact to a Campaign, distinguishing it from sibling tools like sf_campaign_members (list) and sf_create_campaign (create campaign).

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

  Usage Guidelines4/5

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

  Provides explicit instructions: provide campaignId and either contactId OR leadId, and explains status defaults and options. Lacks explicit when-not-to-use or alternatives, 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.

• sf_create_campaignA
  4.3/5.0
  Behavior4/5

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

  Annotations only have destructiveHint: false. Description discloses it creates (mutation), includes default behavior (status defaults to 'Planned'), and return value. Does not cover permissions or rate limits, but adequate for a create tool.

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

  Conciseness4/5

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

  Fairly concise with two sections but some repetition (first line and summary). The [INSTRUCTIONS] tag adds structure. Could be tighter.

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

  Completeness4/5

  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 value (created campaign with ID). Covers required fields, defaults, and date format. Missing error handling details, but sufficient for basic use.

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

  Parameters4/5

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

  Schema coverage is 100%, baseline 3. Description adds extra context: name required, type list, date format, budget meaning. This enhances parameter understanding beyond schema.

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

  Purpose5/5

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

  The description clearly states it creates a Campaign sObject, specifying the verb 'Creates' and resource. It distinguishes from siblings like sf_add_campaign_member and sf_search_campaigns by focusing on creation.

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

  Usage Guidelines4/5

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

  Provides detailed usage instructions including required fields, type options, default status, date format, and return value. Lacks explicit when-not-to-use or alternative tools, but context is clear.

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

• sf_campaign_performanceA
  4.4/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, so safety is already covered. Description adds behavioral detail: the query groups by Type and returns an ROI overview. It consistently notes '[READ-ONLY]'. No contradictions; adds useful 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.

  Conciseness4/5

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

  Two sentences, front-loaded with 'INSTRUCTIONS' and key details. Slightly verbose first sentence but overall efficient. Could be slightly tighter, but no fluff.

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

  Completeness5/5

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

  With no parameters or output schema, the description covers all needed: explains input (none), output structure (list of aggregated metrics), and use cases. Annotations cover safety. Complete for its purpose.

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

  Parameters4/5

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

  No parameters exist, so schema coverage is 100%. The baseline for 0 parameters is 4. The description does not add parameter info because none are needed. Appropriate score.

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

  Purpose5/5

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

  The description clearly states the tool runs aggregate SOQL on Campaign records grouped by Type, listing specific return fields (campaign counts, leads, conversions, costs). It distinguishes from sibling tools like sf_campaign_members (members) and sf_campaigns_by_status (status), making purpose unambiguous.

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

  Usage Guidelines4/5

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

  Explicit use cases are provided: 'marketing dashboard, channel-level performance comparison, or budget allocation analysis.' While it doesn't specify when not to use, the context and sibling list imply alternatives. Slightly missing explicit exclusions, but overall clear guidance.

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