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

No annotations are provided, so the description carries the full burden and does so thoroughly: synchronous blocking, fixed read-only mode, auto-denial of gated tools, permission handling via user settings, and the expert nature of auto_approve. It also discloses the git-based files_touched/scope_violations audit and how denials are surfaced.

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 dense but front-loads the main purpose, read-only guarantee, and synchronous behavior before moving into edge cases. Some repetition around read-only and permission handling keeps it from being maximally tight, but most sentences carry useful information.

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 12 parameters, no annotations, and no output schema, the description supplies the missing behavioral context an agent needs: blocking semantics, fixed mode, denial behavior, permission model, and audit reporting. It is complete enough to select and invoke the tool 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 coverage is 100%, so parameter mechanics are already documented. The description still adds useful semantic context for auto_approve as an expert full-auto switch to pair with sandbox, and clarifies that permissions are granted through the user's own Antigravity settings rather than edited by this server.

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 fast read-only exploration and diagnosis task to the Antigravity CLI. It clearly distinguishes itself from general_task by emphasizing the fixed read-only posture and synchronous blocking behavior.

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 clear usage context for read-only exploration/diagnosis and explains that the mode preset cannot be weakened. It references general_task for comparison but does not explicitly state the reverse condition—use general_task when file modification is intended.

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 does so well: it discloses synchronous blocking, the auto-DENY behavior for gated tool requests and where denials surface (denied_actions), that this server never edits settings.json, that edit_scope is audit-and-replay rather than a sandbox, and that auto_approve is the --dangerously-skip-permissions switch. These are non-obvious side effects an agent must know before calling.

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 with purpose and the synchronous contract, then defaults, then the permission/audit caveats. Dense with little waste, though the auto_approve and sandbox guidance is partly restated and the single long paragraph mixes return-value description with operational warnings.

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?

There is no output schema, and the description compensates by enumerating what the result carries (final response, conversation_id, token usage, denied_actions, files_touched/scope_violations audit when cwd is a git repo). Combined with the timeout/idle-kill semantics in the schema, an agent has enough to call and interpret this 12-parameter tool 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 100%, so the baseline is 3, but the description adds real meaning beyond the schema for edit_scope ('audit-and-replay control, not a sandbox — the CLI writes files itself') and auto_approve ('expert full-auto switch ... pair it with sandbox'). It also states defaults (mode accept-edits, effort medium) that the schema does not.

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?

Specific verb + resource: 'Delegate a general-purpose coding task to the Antigravity (agy) CLI and block until the headless run exits.' The parenthetical '(synchronous; the tool call IS the wait)' immediately separates it from async siblings like watch_task, so an agent can route without opening schemas.

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 concrete operational context: headless runs auto-deny prompting tools, permission must be pre-granted by the user via permissions.allow, file edits inside cwd never prompt, and auto_approve should be paired with sandbox. However, it never names the sibling alternative (explore_task) or states when this blocking tool is preferred over the watch/explore pattern, leaving that inference to the agent.

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 provided, so the description carries the disclosure burden. The verb 'List' implies a non-destructive read and there are zero parameters, so risk is inherently low, but the description says nothing about whether the result is static, scoped, or cached, nor what the entries contain.

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?

One sentence, front-loaded with the verb and resource, with the downstream purpose attached rather than buried. Nothing is redundant.

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 listing tool with no output schema, the description conveys both what is listed and why. It could have sketched the shape of a returned profile (name, description, capabilities), which is the one remaining gap.

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 schema has zero parameters, so the baseline is 4. The description adds a useful cross-tool pointer by naming the `agent` parameter that these values feed, which is more than the empty schema conveys.

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?

Specific verb ('List') plus resource ('agent profiles'), and it goes further by stating the profiles' purpose (values for the `agent` parameter). It does not explicitly distinguish itself from the sibling list_models, but the resource name makes the split inferable.

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 clause 'usable for the `agent` parameter of delegation tools' tells the agent exactly when this tool is relevant — before invoking a delegation tool that needs an agent value. It stops short of naming alternatives or exclusions, so it is clear context rather than full routing guidance.

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 provided, so the description carries the full burden. It discloses the return content (model IDs) and their intended use, but says nothing about whether the list is static or dynamic, its size/format, or pagination — though for a zero-param lister the risk profile is inherently low.

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 sentence that front-loads the verb and resource and adds the one piece of context an agent needs (where the IDs are consumed). No wasted words.

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?

With no annotations, no output schema, and no parameters, the description adequately covers what the tool returns (model IDs) and why they matter. It is sufficient for a trivial lister, though it could note whether the list is stable or environment-dependent.

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 takes zero parameters, so there is nothing for the description to clarify beyond what the schema already conveys. Baseline for a 0-param tool is 4.

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 (List) and resource (model IDs), and scopes it to a concrete purpose: values usable for the `model` parameter of delegation tools. This distinguishes it from list_agents and the task tools, though it does not name a sibling explicitly.

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 it by naming the `model` parameter of delegation tools as the consumer of these IDs, which is a useful contextual hook. However, it never states when to call it versus siblings or any prerequisite conditions, leaving usage implicit.

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 provided, so the description carries the full burden, and it does disclose useful behavior: it can watch runs in any session, and the returned 'running' plus 'modified' fields let an agent distinguish a live run from an abandoned one. It does not cover blocking behavior, cost, or permission requirements, but 'tails a transcript' clearly implies a read-only operation.

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, front-loaded with the core action, then the default-argument behavior, then the call condition. Nothing is wasted and no sentence repeats the schema or title verbatim.

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 two-parameter read-only tool with no output schema, the description covers what it does, when to invoke it, the cross-session scope, and the meaning of the key return fields. An agent has everything needed 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema by stating that zero arguments selects the latest run, which ties the two optional params to a concrete default scenario. The remaining specifics (tail counts, path forms) are fully documented in the schema.

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 ('Tails a task's live stream transcript') and scopes it precisely to observing a run rather than starting one. The relationship to general_task/explore_task makes it distinguishable from the sibling set, which otherwise contains only task-launching and listing tools.

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 an explicit trigger ('Call it while a general_task/explore_task is in flight (this or any session)'), including the cross-session case, plus the default behavior with no args. It stops short of stating when not to use it (e.g. after a run is complete, or vs. reading a finished log).

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