Server Quality Checklist

Tool Scores

• delegate_backendA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this can modify the workspace. The description adds the mode distinction (analyze/review read-only vs implement edits), which is useful behavioral context. However, it doesn't disclose side effects like parallel risk, workspace mutations beyond targeted files, or concurrency behavior that a destructive tool might warrant.

  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?

  Two sentences, zero filler. The first sentence states purpose and scope; the second adds the crucial read-only vs. edit mode guidance. Every word earns its place.

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

  Completeness3/5

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

  This is a delegation tool with 9 parameters and a destructiveHint, no output schema. The description explains purpose and mode but doesn't cover interaction with same-domain sibling tools or failure/partial-success behavior. Given the schema richly documents all 9 parameters and the description covers the core behavioral distinction (read-only vs edit), it's adequate but not comprehensive.

  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% with detailed parameter descriptions, so baseline is 3. The description adds value by explaining the domain-appropriate use of the tool and the mode semantics (read-only vs edits), reinforcing the 'mode' parameter's behavioral meaning beyond its schema description. It complements rather than repeats the 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 uses a specific verb ('Delegate') with a clear resource ('backend, API, database, auth, infrastructure, security, performance, or backend-test work to Codex'). It clearly distinguishes from siblings by listing the backend domains, and the closest sibling (delegate_frontend) is differentiated by the explicit domain list.

  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 provides clear guidance on when to use this tool ('Delegate backend...work') and distinguishes read-only vs. editing modes ('Use analyze/review for read-only work and implement for edits'). It lacks explicit 'when NOT to use' exclusions or named alternatives beyond the domain itself, but the mode guidance is valuable context.

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

• specialist_statusA
  4.1/5.0
  Behavior3/5

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

  Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the valuable nuance about not verifying authentication, which is not evident from annotations or schema. However, it doesn't disclose the return format or what a failure looks like, though with zero params and a simple check, this is reasonably adequate.

  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?

  Two sentences, zero waste. First sentence states the core purpose; second sentence names a critical limitation. Every element earns its place and the information is front-loaded.

  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?

  For a zero-parameter, simple status check with complete annotations and 100% schema coverage, the description is essentially complete. It names the tools checked, clarifies what it doesn't verify, and fits naturally with sibling delegate tools. The only minor gap is not describing the output format, but that's a modest concern given no output schema is provided.

  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?

  The tool has zero parameters, so there is nothing for the description to explain. Per the rubric, 0 params = baseline 4, and the description earns a 5 by explicitly naming the three CLIs checked and adding context about what is NOT covered (authentication), providing more than the schema could.

  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?

  Description clearly states 'Check whether the configured Codex, Kimi, and Grok CLIs are available' with a specific verb (Check) and resource (CLI availability). It goes beyond a bare statement by explicitly naming the three CLIs, which distinguishes it from the sibling delegate tools that perform delegation actions rather than status checks.

  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 clarifies it does NOT verify account authentication, which is a useful exclusion that tells the agent when this tool is not sufficient. It implies this is a pre-flight check before delegating work, given the sibling tools are delegate_backend/delegate_frontend. A clear when-not is provided via the authentication disclaimer.

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

• delegate_buildA
  4.4/5.0
  Behavior4/5

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

  Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds value by spelling out the routing behavior (backend→Codex, frontend→Kimi), the 'never for speed' caveat, and the mode-dependent editing semantics. It also flags the possibility of 'mechanical repository-wide transformations,' which implies potentially broad changes. 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.

  Conciseness5/5

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

  Four tight sentences, each earning its place. The first sentence front-loads the purpose with a verb and resource, followed by explicit routing rules, a caution, and mode semantics. No fluff, perfect density.

  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 9 parameters, strong annotations, and sibling tools, the description covers all key aspects: purpose, routing, when-not-to-use, and mode distinctions. The only omission is a description of what this tool returns or how to check results, but the presence of a sibling tool 'specialist_status' likely covers monitoring. For a delegation tool, this is nearly 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 description coverage is 100%, so every parameter already has a description. The tool description goes slightly beyond the schema by giving examples of what belongs in 'task' (dependency upgrades, CI automation, lint cleanup), which helps the agent form a task. This is marginal added value, so the baseline of 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 opens with a clear directive: 'Delegate domain-neutral build tooling, dependency or toolchain upgrades, CI and release automation, mechanical repository-wide transformations, generated boilerplate, or test and lint cleanup to Grok Build.' This specifies the exact resource (Grok Build) and enumerates concrete task domains. It also explicitly differentiates from sibling tools by assigning backend work to Codex and frontend/UX work to Kimi, making the division of responsibilities unmistakable.

  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 explicit when-to-use guidance: list of accepted task types. It also gives exclusions: 'Backend behavior belongs to Codex and frontend or UX behavior belongs to Kimi unless the user explicitly overrides routing.' A strong caution, 'Never choose Grok solely for speed,' and mode guidance ('Use analyze/review for read-only work and implement for edits') round out comprehensive usage instructions.

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

• delegate_frontendA
  4.5/5.0
  Behavior4/5

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

  Annotations declare destructiveHint=true and readOnlyHint=false, and the description reinforces this by distinguishing read-only modes (analyze/review) from implement which 'may edit the workspace.' The description adds valuable context about the mode-dependent mutation behavior that goes beyond the raw annotation flags, clarifying that not all invocations are destructive. This is a meaningful addition though the safety profile is partially covered by 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 a single focused paragraph that front-loads the purpose and enumerates domains concisely. The mode guidance is packed efficiently. It could arguably be slightly tighter, but every sentence earns its place and there is no fluff or repetition. Slightly below perfect due to the long enumeration, but appropriately sized for a complex delegation tool.

  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 the tool's complexity (9 parameters, delegation semantics, mutation risk) and the absence of an output schema, the description does a solid job covering purpose, safety, and mode selection. The 100% schema coverage handles parameter documentation. The main gap is the absence of guidance on structuring tasks or what success looks like, but acceptance_criteria parameter provides an observable-contract mechanism. Adequately complete for a delegation 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% and all parameters have descriptions in the schema, so the baseline is 3. The description adds value by clarifying the analyze/review/implement mode distinction and its behavioral implications, which enriches understanding of the mode parameter beyond its schema description. The task and scope fields are self-explanatory, but no substantial additional semantics are needed given the schema's completeness.

  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 uses specific verbs ('delegate') plus comprehensive resource enumeration (product design, UX, visual systems, components, styling, accessibility, responsive behavior, animation, client state, frontend-test). It clearly distinguishes from sibling delegate_backend (backend specialization) by listing frontend-specific domains. The 'analyze/review vs implement' split adds meaningful scope.

  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 explicitly instructs when to use which mode: 'Use analyze/review for read-only work and implement for edits.' This gives clear contextual guidance. Combined with the mode enum in the schema and sibling specialization contrast (backend), the when-to-use guidance is strong and actionable.

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