Server Quality Checklist

Tool Scores

• antigravity_runA
  3.7/5.0
  Behavior5/5

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

  With no annotations, the description carries full responsibility and does an excellent job: it discloses authentication requirements ('using your existing Antigravity login (no API key)'), resolution behavior ('never silently substituted'), return contents ('git-verified files_changed and scope_violations'), and retry policy ('AgentBridge never retries on its own'). No contradictions exist.

  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 only four sentences, each earning its place: delegation mechanism, resolution policy, return value summary, and retry semantics. It is front-loaded with the primary action and free of redundant filler.

  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 tool with 12 parameters, no output schema, and no annotations, the description covers key operational context: auth, resolution, returns, and retry policy. It lacks guidance on when to prefer this over codex_run and what happens if the CLI is unavailable, but the 100% schema coverage compensates for parameter-level details.

  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 the baseline of 3 applies. The description does not add new parameter-level semantics beyond what the schema already provides; it only references the model/effort resolution vaguely, which is adequately covered in the parameter descriptions.

  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 the tool's purpose: 'Delegate a task to the Antigravity CLI (`agy`) running as an external worker.' It specifies the verb, resource, and distinctive auth behavior (no API key). However, it does not explicitly differentiate from sibling tools like codex_run, even though the Antigravity-specific naming implies it.

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

  Usage Guidelines2/5

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

  The description provides no guidance on when to use this tool versus alternatives (codex_run, bridge_status). It mentions 'One call = one attempt' and 'never retries' as behavioral facts, but does not state usage conditions, prerequisites, or when to choose a different tool. Relevant routing advice (e.g., 'extra high' → Codex) is buried in the parameter descriptions, not the main description.

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

• codex_runA
  4/5.0
  Behavior5/5

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

  With no annotations, the description fully discloses critical behaviors: authentication via existing login, per-call model/effort choices, git-verified files_changed and scope_violations, the verification block auto-run by AgentBridge, skip_verification semantics, and the no-retry policy. It also mentions error behavior (requested_model_unavailable) in schema but the main description adds substantial context beyond the structured fields.

  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 dense but every sentence adds value, covering purpose, authentication, behavioral semantics, and verification details. It is front-loaded with the core action and flows logically. Slightly long but appropriate for a 15-parameter tool; no fluff detected.

  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 the tool's complexity (15 params, no output schema), the description is remarkably complete. It explains the verification process, git-verified outputs, retry behavior, and model availability handling. It does not detail return value structure, but since there is no output schema, the description covers the essential outcomes (result, files_changed, scope_violations, verification block) sufficiently.

  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 the baseline is 3. The description adds minimal parameter-specific meaning beyond what schema provides; it does note that model is passed verbatim and verification runs without a shell, but these are already in schema descriptions. No extra compensation needed, but also no significant enhancement.

  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 delegates a task to the Codex CLI external worker, specifying the resource (Codex CLI) and the verb (Delegate). It distinguishes from siblings by naming Codex explicitly, and includes details like 'no API key' and 'one call = one attempt' that set it apart from antigravity_run.

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

  Usage Guidelines2/5

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

  The description provides no explicit guidance on when to use this tool versus antigravity_run or bridge_status. It mentions configuration behavior (model/effort per call, no global inheritance) and retry policy, but fails to state conditions for selecting this tool over alternatives. This is a gap given the sibling tools.

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

• bridge_statusA
  4.6/5.0
  Behavior5/5

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

  With zero annotations provided, the description fully carries the transparency burden and excels: it discloses a no-inference cost guarantee, an explicit epistemic honesty policy ('reported as unverified rather than guessed'), and a security guarantee ('Never returns credentials'). These behavioral traits go well beyond what the empty schema reveals.

  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?

  Three prior sentences, each earning its place: scope, then cost/accuracy behavior, then security. The second sentence is list-heavy but necessary since no annotations or output schema exist — the description is the sole documentation. Slightly long but never wasteful.

  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 low-complexity 0-param, read-only tool with no annotations and no output schema, the description is the only source of truth and covers all critical operations: exact contents of the report, inference cost (none), accuracy semantics (unverified vs guessed), and credential safety (never). Nothing material is left unstated.

  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 tool has zero parameters and an empty schema, so the baseline of 4 per the rubric applies. The description adds no conflicting param info; the only implied input is the health-report scope itself, which is irrelevant for a no-arg call. No compensation needed for schema gaps.

  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?

  Starts with a specific verb+resource ('Report AgentBridge health') and exhaustively enumerates the report's scope: version, directory, CLIs, model availability, model ids, jobs, warnings. This specificity clearly delineates it from siblings codex_run/antigravity_run, which are execution-oriented, making the health/introspection function unmistakable.

  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 health/introspection framing implies pre-flight or diagnostic use (checking sign-in state, git verification, per-model availability) with clear context. However, no explicit exclusions or named alternatives appear in the description; sibling distinction is inferred from context rather than stated.

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