Server Quality Checklist

Tool Scores

• statusA
  4.2/5.0
  Behavior5/5

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

  With no annotations, description fully carries burden. It discloses self-healing (resets if credentials lost), refresh behavior (busts 30-min cache, noop without tenant), and fallback behavior (bundled snapshots, live calls unavailable). Comprehensive and actionable.

  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?

  Well-structured with main purpose first, followed by details. Each sentence adds value, though slightly verbose (e.g., explaining fallback in first paragraph could be tighter). Still effective.

  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 what the tool shows (status info). Covers key behaviors, param usage, prerequisites, and edge cases. Missing explicit output format, but sufficient for a status 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% for the single parameter. Description adds meaning by explaining the purpose of refresh and its effect (force fresh discovery, noop when no tenant), which goes beyond the schema's description.

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

  Purpose4/5

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

  The description clearly states it shows CLI status including tenant credentials, active tenant, and API namespaces. It distinguishes from the sibling tool 'codemode' only implicitly by describing its own scope, but lacks explicit differentiation.

  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 when to use: checking status, and when to use refresh flag (after subscribing/unsubscribing microservices). Mentions prerequisite (set-active-tenant if no tenant active). However, does not explicitly state when not 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.

• codemodeA
  4.9/5.0
  Behavior5/5

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

  The description discloses critical behaviors not covered by annotations: every result starts with a marker line for tenant verification; active tenant is global to the session; live API calls fail without an active tenant; methods may return 404 if the service isn't installed; discovery is omitted for blocked methods; and blocked requests fail with explanatory messages. It also warns about context flooding from large payloads and instructs the agent to verify tenant before reporting.

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

  Conciseness5/5

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

  The description is long but tightly structured: it opens with the most critical warning ('Read first'), then explains the globals with precise JSDoc-style comments, then gives a numbered workflow followed by examples. Every section earns its place—there's no filler. The front-loading of tenant verification and costly-call warnings is excellent.

  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?

  The description is exceptionally complete for a tool that executes arbitrary code. It covers tenant semantics, discovery workflow, failure modes, blocking policies, return conventions, and examples. Since there's no output schema, the description explains the return format ('Return the final value you want; on success it is returned in Toon format'). For a highly complex tool, this is near-exhaustive.

  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?

  The description adds significant meaning beyond the basic schema's `code` parameter. It explains that the code must be an async function expression, that globals are automatically available, and that the final value is returned. It also provides multiple examples. However, the schema itself fully covers the parameter (100% coverage), so the description's additional value is solid but not exhaustive.

  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 an async JavaScript function against the Cumulocity API and provides discovery, documentation, and typed API calls within one function. It names the specific global objects (codemode, docs, c8y) and explains the workflow, distinguishing from sibling tools (status, set-active-tenant) which manage connection state rather than execute code.

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

  Usage Guidelines5/5

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

  The description provides an explicit, mandatory workflow: describe() → search → describe(shortlist) → call. It strongly emphasizes using discovery first to avoid expensive calls, warns against relying on prior knowledge, and gives detailed guidance on when to use docs.search/read and how to prefer server-side filtering. It also explicitly tells the agent to return only needed data and not raw unfiltered collections.

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

• set-active-tenantA
  5/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full responsibility for behavioral disclosure. It clearly states persistence across sessions, the effect of clearing, fallback to bundled-only browsing, and unavailability of live API calls until a tenant is set again. This is excellent transparency for such a simple state-setting tool.

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

  Conciseness5/5

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

  The description is three sentences with every sentence earning its place: core action, persistence/constraint, and fallback behavior. It is front-loaded and contains no filler or redundancy.

  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?

  For a one-parameter tool with no output schema and no annotations, the description is complete. It covers setting, clearing, valid input source, persistence, and downstream behavior, giving the agent enough context to select and use the tool correctly without additional lookups.

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

  Parameters5/5

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

  Despite the reported 0% schema description coverage, the tool description fully compensates by explaining that tenantUrl must match a value from the status tool and that null clears the active tenant. With only one parameter, this gives the agent everything needed to invoke the tool correctly.

  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 sets or clears the active Cumulocity tenant, with explicit mention of the null value to clear. It uses a specific verb and resource, and distinguishes itself from status and codemode by connecting tenantUrl to status output and explaining fallback behavior.

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

  Usage Guidelines5/5

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

  The description gives explicit usage guidance: call once at session start or when switching tenants, pass null to clear, and understand that codemode discovery remains available but live API calls do not. It also tells the agent that the value must come from the status tool, providing clear context for when to use this tool vs alternatives.

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