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

With no annotations, the description carries the full burden. It does disclose real behavioral traits beyond the name: routing to a different model family (Gemini Pro) and an adversarial hunting posture covering edge cases, security issues and unstated assumptions. It omits cost/latency implications of a second-model call, whether content is sent externally, and what a review returns (there is no output schema).

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 what and the model-family detail, then the usage triggers. The trailing list 'flaws, edge cases, security issues, and unstated assumptions you may have missed' is slightly padded and 'you may have missed' restates the adversarial premise.

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?

All five parameters are optional, so the agent must decide for itself that content or files is required to make the call useful, and the description never says so. Combined with no output schema and no note on what a review produces or costs, the definition is workable but leaves meaningful gaps for a tool that spends a second model call.

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 all five parameters are already documented, and the description does not discuss any of them. It implicitly maps 'plan', 'design', 'code review' to the content/files inputs but adds no syntax, precedence, or combination rules beyond the schema. Baseline 3 applies.

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?

Names a specific verb+resource: an adversarial second opinion sourced from a different model family (Gemini Pro), with the issue classes it targets. It is clearly distinct from web_lookup and deep_search, but it never distinguishes itself from the sibling 'delegate', which is the one tool an agent could plausibly confuse it with.

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?

Gives explicit when-to-use triggers: plan critiques, design reviews, pre-merge code review, and states them emphatically ('ALWAYS'). It offers no when-not guidance and never names an alternative tool, so an agent still has to infer the boundary against 'delegate' or 'analyze_files'.

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?

With no annotations supplied, the description carries the full burden and does disclose the single most important behavioral trait: the files never enter the agent's context and only the answer returns. That is exactly the non-obvious fact an agent needs in order to decide between this and reading files directly. It leaves out secondary behavior such as latency/cost, authentication requirements for the external CLI, and what happens when a file path is invalid or too large.

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, each earning its place: the action and mechanism first, the trigger conditions second, the payoff (context savings) last. The imperative 'USE THIS' is front-loaded where a scanning agent will catch it, and there is no redundant restatement of the tool name.

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 four-parameter delegation tool with no annotations and no output schema, the description covers the decision-relevant essentials: what it does, when to reach for it, and that only a synthesized answer comes back. The remaining gap is what that answer looks like and how failures surface, which matters somewhat because there is no output schema to describe the return shape.

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 explains cwd, files, model, and question thoroughly, and the description adds no syntax, format, or routing detail beyond it. The baseline of 3 applies; the one thing it could have added, guidance on when to override the model, is already deferred to the schema's 'Normally omit' note.

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 names a specific verb and resource ('Delegate file analysis') plus the mechanism ('Antigravity CLI (Gemini)'), and explicitly contrasts it with the default behavior ('instead of reading files yourself'). An agent can immediately tell this apart from sibling tools like deep_search or web_lookup, which operate on the web rather than on local files.

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?

It gives concrete, actionable triggers — files over 200 lines, tasks spanning more than 3 files — and enumerates the shapes of work it suits (logs, database dumps, generated code, cross-file reviews, comparisons). What's missing is the inverse guidance: when NOT to use it (e.g., small files, single-file edits, cases where exact file contents must be quoted back), and no sibling tool is named as the alternative.

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?

With no annotations, the description carries the full burden; it does disclose meaningful behavior — that work is delegated to an external CLI and that the point is context economy. It does not say whether the operation is strictly read-only, what the response looks like (report vs. raw hits), or anything about latency/cost of spawning a CLI agent.

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 delegation model, then the concrete capability list, then the selection rule. No filler; even the 'archaeology' metaphor earns its place by framing history-focused search.

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 three-parameter, one-required tool with no annotations and no output schema, the description covers intent and routing well. The notable gap is return shape and safety profile — an agent cannot tell from this text what it gets back or whether the CLI can touch the working tree.

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 cwd, model, and query are all documented in the schema and baseline 3 applies. The description's example phrasings ('when/why did X change', 'where is Y used') usefully signal that query should be natural language, but that meaning is largely already conveyed by the schema's own example.

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 gives a specific verb-plus-resource ('Delegate codebase archaeology... git log/diff/blame spelunking, wide greps') and concrete example intents, so an agent knows exactly what class of work it covers. It does not name or contrast the sibling tools (analyze_files, web_lookup, delegate), leaving the codebase-vs-file-analysis boundary implicit.

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?

'USE THIS instead of running many search commands yourself — it saves your context' is an explicit selection rule with the alternative it displaces. It stops short of stating when NOT to use it (e.g., a single known file read, or a plain web lookup), so the exclusion side is missing.

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?

With no annotations, the description carries the full burden, and it does disclose the key trait: agy has full tool access (shell, file reads, web) within the given cwd, so an agent knows this can mutate files and execute commands. However, it says nothing about blocking behavior, timeouts, cost, permissions, or whether shell execution is sandboxed — significant gaps for an unrestricted delegation tool.

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 filler, with the core identity and the risk-relevant capability disclosure front-loaded. Every clause 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?

For a powerful, unannotated delegation tool with no output schema, the description omits what comes back (raw text, transcript, artifacts), whether the call blocks until completion, and any timeout or cost ceiling. The capability disclosure is useful but the operational picture is 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 description coverage is 100%, so cwd, model, and prompt are already documented in the schema, including the advice to normally omit model. The description only reinforces cwd scoping ('in the given cwd') and adds no format or content guidance for prompt beyond 'complete task prompt.' Baseline 3 applies.

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?

States a specific verb and resource: raw delegation to the Antigravity CLI (agy), scoped to 'heavy tasks that don't fit the other tools.' The agent can tell this is a general-purpose escape hatch, though it never names which sibling (deep_search, analyze_files) it replaces in a given situation.

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?

Offers a loose exclusion criterion ('tasks that don't fit the other tools') but no positive selection criteria and no named alternatives or prerequisites. Usage is implied rather than spelled out, leaving the agent to guess when delegation beats a dedicated sibling 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?

With no annotations at all, the description carries the full disclosure burden. It does add real behavioral context — that the prior context lives on agy's side and need not be resent — but says nothing about what happens with an invalid or expired session_id, whether the call can trigger side effects, or how model/cwd overrides interact with the resumed session.

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, zero waste, and the operational constraint (context already on agy's side, nothing to resend) is front-loaded where the agent will act on 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?

For a four-parameter continuation tool with no output schema and no nested objects, the definition covers the essential behavior — session continuity and no resend. Missing only edge-case behavior around invalid sessions, which is a modest gap rather than a blocking one.

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 all four parameters are already documented in the schema. The description adds only a marginal gloss on session_id ('returned by every other tool'), leaving cwd and model entirely to the schema. 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?

States a specific verb and resource — 'Continue a previous Antigravity session by session_id' — and immediately scopes it to follow-up questions about a prior delegation, which cleanly separates it from delegate and the other siblings. An agent can identify the tool without opening the schema.

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?

Gives explicit when-to-use guidance ('USE THIS for follow-up questions about a prior delegation') and explains why no payload resend is needed. It stops short of naming delegate as the alternative for new work or stating what to do when a session is missing/expired, so the routing guidance is clear but not fully closed.

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?

With no annotations, the description carries the full burden; it usefully discloses the backend (Antigravity CLI, Gemini with web access), which tells the agent this is an outbound delegated call. It says nothing about whether the operation is read-only, latency or cost characteristics, failure modes, or what the response looks like.

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 mechanism and followed by the usage trigger. No wasted words and no redundancy with the schema.

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 tool with no annotations and no output schema, the description should indicate what comes back — raw page text, a synthesized answer, or citations — since the schema cannot. It also omits any note on result freshness or scope limits, leaving an agent unable to predict the return value's shape.

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 query, cwd, and model are already documented in the schema, including the advice to normally omit model. The description adds no guidance on how to phrase the query or when to supply cwd, so baseline 3 applies.

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?

States a specific verb and resource — delegate a web/documentation lookup to the Antigravity CLI — and enumerates the content types it handles (library docs, API references, error messages, current versions). It does not differentiate itself from plausible siblings like deep_search or delegate, so an agent still has to infer the boundary.

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 'USE THIS when you need information you don't have or that may be newer than your training data' clause gives a clear positive trigger. However, it names no alternatives and no exclusions, so the choice between web_lookup, deep_search, and delegate is left unstated.

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