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

With no annotations, the description fully carries the behavioral disclosure burden. It reveals that the agent has file tools, that workspace grants read+write access, that prompt_file wins over prompt, that cleanup deletes the prompt/system files, and that save_artifact always writes an artifact. These are meaningful behavioral traits that directly inform safe invocation.

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?

The description is front-loaded with a one-sentence purpose, followed by a brief behavior paragraph and a clean parameter list. Every line adds operational value with no filler, making it appropriately sized for an 11-parameter tool.

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?

Given the tool's complexityed—11 parameters, file-wielding agent, potential workspace modifications—the description covers defaults, workspace semantics, resume mechanics, cleanup, artifact saving, and model options. Since an output schema exists, return-value details are unnecessary. Nothing critical is missing for an agent to invoke it correctly.

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 0%, but the description supplies a semantic gloss for every single parameter, including precedence rules, special values like workspace='none', default behaviors, and side effects. This fully compensates for the schema's lack of descriptions.

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 opens with a specific verb and resource: 'Ask the Google Antigravity AGENT (Gemini 3.8 Flash / Pro)' and clearly characterizes it as a coding agent with Read/Write/Bash tools, comparable to Claude Code or Codex. This makes the tool's identity and scope immediately distinguishable from a generic ask-gemini sibling.

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 description gives clear context for when to use the tool: 'By default it works in the current directory... so it can read and run your repo like Codex,' and highlights distinguishing features like parallel swarm execution and one-click resume. It stops short of explicitly naming alternatives or when not to use it, so it lacks full exclusionary routing.

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?

No annotations are present, so the description carries the full burden of behavioral disclosure. 'Alias for ask-antigravity' reveals nothing about side effects, permissions, rate limits, statefulness, or operation type. The description is behaviorally empty.

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?

The description is one sentence long, but it is under-specified rather than appropriately concise. It communicates only an alias relationship and provides no real content. This is under-specification, not efficient brevity.

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 11 parameters, no annotations, and no parameter descriptions, the alias-only description is wholly insufficient. An agent cannot correctly determine required inputs or expected behavior. Even with an output schema, this definition 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 0%, and the description compensates with no parameter information whatsoever. All 11 parameters, including model, effort, prompt, resume, system, and conversation_id, receive no explanation in either schema or description. This is a severe gap.

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 only states that this tool is an alias for ask-antigravity, without specifying the actual function. It does not mention asking questions, generating responses, or interacting with a model, so an agent cannot determine the tool's purpose from the description alone. It is not a strict tautology, but it's a cross-reference that provides no substantive meaning.

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 description implies equivalence with ask-antigravity but gives no explicit guidance on when to use this tool versus alternatives. It does not mention selection criteria, prerequisites, or exclusions. The alias nuance is weak guidance at best.

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 discloses that data is live, that it covers remaining quota percentages, and that health status levels are Healthy / Low / Depleted. The phrase 'Retrieve and display' also implies a read-only behavior, which is adequate for a zero-parameter check 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 short sentences, no filler, with the core action and scope in the first sentence and the output categories in the second. Every word 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 no-argument read-only quota checker with an output schema, this description is complete: it names the resource, the metric, the scope, and the status categories. There is nothing an agent needs to call it correctly that is missing.

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?

The tool has zero parameters, so there is little to document. The baseline for zero-parameter tools is 4, and the description adds useful scope context ('all Google Antigravity models') without needing to explain inputs.

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 states a specific action ('Retrieve and display') and a precise resource ('live remaining quota percentages for all Google Antigravity models'). It clearly separates this from siblings like list-models or ask-gemini by focusing on quota health rather than model names or model interaction.

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 intended use is clear: when an agent needs current quota status and health for Antigravity models. While it does not explicitly name alternatives or exclusion conditions, the context is unambiguous and there are no prerequisites or competing workflows implied by the description.

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 provided, the description carries the full burden of behavioral disclosure. It does disclose the write_to_file behavior ('If True, writes the generated tests directly into output_file') and reveals defaults for test_framework and model. However, it does not explain what happens when write_to_file is False, whether existing files are overwritten, whether the tool makes external API calls via the model parameter, or whether the target file is modified in any way.

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?

The description is efficient and well-structured. A single sentence states the purpose, followed by a cleanly formatted parameter list. Every line adds information, and the most important behavioral switch (write_to_file) is described in its own line. No filler or redundant content.

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?

The tool has six parameters, no annotations, and an output schema (which presumably explains return structure). The description covers all parameters and the core purpose, but leaves open important operational questions: what happens if write_to_file is false, does it create/overwrite directories, and what file types or languages are supported. Given the presence of an output schema, return-value documentation is not the main gap, but operational behavior could be more complete.

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 0%, so the description must compensate, and it largely does. Each of the six parameters receives a meaningful explanation: target_file specifies relative/absolute path, test_framework gives concrete examples and a default, output_file includes a sample path, and write_to_file explains its effect. A few descriptions remain thin (workspace is just 'Workspace root directory'), but overall the parameter semantics are solidly above baseline.

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 opens with a clear verb and resource: 'Generate thorough unit tests for a specified source code file.' It is immediately distinguishable from sibling tools like ask-gemini, review-diff, or ping, which serve different purposes. The scope (source code file) and action (generate tests) are specific and unambiguous.

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 description implies when to use the tool—whenever unit tests are needed for a file—but it never explicitly contrasts this with alternatives such as ask-gemini or ask-antigravity, which could also generate test code conversationally. There is no when-not-to-use guidance or prerequisite clarification, so usage context is implied rather than stated.

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?

There are no annotations, so the description carries the burden of explaining behavior. 'List' conveys a read-only intent and no destructive side effects are implied or hidden. However, it does not disclose any additional behavioral details such as authentication requirements, rate limits, or whether the list is cached.

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?

A single concise sentence delivers the essential information with no filler. The action, resource, and context are all front-loaded and every word is meaningful.

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 zero-parameter list tool with an output schema, this description is nearly complete. It identifies what the tool surfaces and the service context. The only notable gap is the lack of guidance about how this fits into the workflow alongside sibling tools, but the low complexity limits the impact of that omission.

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?

The tool has zero parameters and the schema coverage is effectively complete, so no parameter-level explanation is needed. With 0 params, the baseline is 4, and the description does not need to compensate for any schema gaps.

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 uses a specific verb ('List') and resource ('available models') scoped to 'Google Antigravity', making the tool's purpose immediately clear. It also stands apart from the sibling tools, which focus on asking, reviewing, checking, generating, and pinging.

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?

No guidance is provided about when to use this tool versus the alternatives. An agent can infer it is a preliminary discovery step before using ask-antigravity or ask-gemini, but the description does not state this explicitly.

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 must carry the full burden. It reveals that the tool verifies responsiveness, but it does not disclose that an optional prompt is sent, what the success/failure response looks like, or whether there are any side effects. 'Verifies' hints at read-only behavior, but too much is left to inference.

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?

The description is one short sentence, front-loads 'Health check,' and avoids repeating the tool name (ping) as a verbatim label. It could not be more concise.

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 simple, optional-parameter ping, the description plus schema covers the basic call: run with no arguments and get verification. However, it is incomplete because the prompt parameter is unexplained and no usage context is given; this is adequate but has clear gaps.

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 0%, and the description does not mention the prompt parameter at all. The schema gives only a title and default, so an agent cannot tell why prompt exists or how it affects the health check.

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 states a specific action and resource: 'verifies that the Antigravity CLI or backend responds,' clearly identifying a health-check tool. This is distinct from the sibling tools (ask, review, generate, list, check-quota) even without naming them.

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?

No guidance is given about when to run this check versus using a sibling tool such as ask-antigravity or check-quota. The phrase 'Health check' implies pre-flight connectivity verification, but the description never states this or any exclusions.

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?

No annotations are present, so the description carries the burden. It explicitly discloses 'strictly read-only mode' and that it 'never modifies your repository files', which is important safety-relevant behavior. It does not mention other side effects such as external model calls or quota usage, but the core non-destructive behavior is clearly stated.

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?

Front-loaded purpose, followed by a single behavioral guarantee, then a clean, scannable parameter list. Every sentence contributes needed information and there is no filler.

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?

An output schema exists, so return-value details are not required. All parameters are documented with defaults and the diff scope is clear. The only minor gap is that available model IDs are not enumerated, but the model is optional and has a default, and list-models exists as a sibling.

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 0%, btut the descriprtion compensates fully by explaining all four parameters: workspace path with default, staged boolean with diff semantics, focus with concrete examples, and model with default ID. This is exactly the semantic layer the raw schema lacks.

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: 'Perform an automated, structured code review' on 'current uncommitted or staged git changes'. This clearly separates it from conversation-oriented siblings like ask-gemini and ask-antigravity, and from generate-tests, which generates tests rather than reviewing diffs.

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?

Provides clear context: the tool reviews uncommitted or staged changes, with the staged param deciding which diff to examine. It does not explicitly name alternatives or state when not to use it, so not a 5, but an agent can infer the intended sitatuation reliably.

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