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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing beyond the action itself. It does not say whether cancellation is irreversible, whether the job's partial output is retained or discarded, what happens if the job already finished, or what the tool returns. For a destructive lifecycle operation this is a significant gap.

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 front-loaded sentence with zero filler; the action and its target are stated immediately.

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 one-parameter tool with a fully documented schema and no output schema, the definition is minimally viable. It is still missing the behavioral facts an agent needs before invoking a cancellation (irreversibility, effect on job output, behavior on already-completed jobs).

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% and the single job_id parameter is documented in the schema ('The job ID to cancel.'), so the baseline of 3 applies. The description adds no format, sourcing, or lookup guidance (e.g. obtaining the ID from list_active_jobs) beyond 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?

The description states a specific verb and resource ('Cancel a running background subagent job'), which an agent can distinguish from the read-oriented siblings check_agent_job and list_active_jobs by verb alone. It stops short of explicitly naming a sibling or contrasting scope, so it lands at 4 rather than 5.

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?

There is no when-to-use guidance, no prerequisites (e.g. the job must still be running), and no mention of alternatives or follow-up tools such as check_agent_job. The word 'running' hints at a precondition but leaves it to inference.

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 behavioral burden as a single terse sentence. It never states that the operation is read-only, whether it blocks or polls, whether log output is truncated or streamed, or how it behaves for a still-running versus failed job.

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, zero filler, and the object of the operation is front-loaded before the enumerated return facets. Nothing here fails to earn 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?

With no output schema and no annotations, the description usefully compensates by naming what comes back (status, logs, duration, output). It still omits polling/streaming behavior and terminal state handling, which an agent monitoring a job would want.

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% for the single job_id parameter, and the schema description even cites dispatch_gemini_agent as the source and gives an example format. The prose adds no meaning beyond the schema, so the baseline of 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?

The description pairs a specific verb ('Check') with a specific resource ('a dispatched agent job') and enumerates the returned facets (status, logs, duration, output), which is clearer than the bare name. It implicitly distinguishes itself from dispatch_gemini_agent by noting the job is already dispatched, but it does not explicitly contrast itself with list_active_jobs or cancel_agent_job.

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?

There is no guidance on when to use this tool versus list_active_jobs (which also surfaces jobs) or cancel_agent_job. The dependency on a prior dispatch is only hinted at through 'dispatched', leaving the workflow condition to inference.

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 behavioral trait: asynchronous, non-blocking execution that returns a job_id immediately. However, it omits the rest of the job lifecycle — that the job runs in the background and must be polled, whether it can be cancelled, failure behavior, and any auth/session prerequisites (the model param hints at dependence on the connected IDE 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 tight sentences with zero filler. The core action is front-loaded and the non-blocking return contract is stated second, which is exactly the right ordering.

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, so the description usefully states the return value (a job_id). Combined with full parameter coverage, an agent has enough to invoke the tool. The remaining gap is the lifecycle handoff — it never points at check_agent_job or cancel_agent_job for the dispatched job.

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 four parameters are already documented, including the pointer to list_available_models for the model param. The description adds no additional parameter meaning, so the baseline of 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: dispatching coding/analysis/research work to a background Antigravity subagent, and it names the async nature (returns immediately with a job_id). It does not explicitly contrast itself with siblings like gemini_code_search or check_agent_job, but the dispatch semantics are unmistakable.

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?

Usage is implied rather than stated: 'background' and 'orchestrator is never blocked' suggest long-running work that shouldn't be awaited inline. There is no explicit when-to-use vs. gemini_code_search, and no instruction to follow up with check_agent_job or cancel_agent_job — the natural next steps are left for the agent to infer.

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 full behavioral burden. It discloses synchronous execution and that an answer is returned, which is useful context. But it omits important operational details such as file-size limits, model cost, error behavior, and what exactly the answer contains.

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 efficient sentences with no wasted words. The opening 'Use a large-context model...' is slightly indirect, but the core action and synchronous behavior are front-loaded enough for quick comprehension.

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 covers the basic purpose and synchronous nature but leaves gaps regarding limits, cost, error handling, and return format. It is minimally adequate but not complete enough to fully guide correct invocation.

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 documents both parameters thoroughly. The description adds no syntax, format, or constraint details beyond what the schema provides, making the baseline 3 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: scans multiple repository files and answers architectural or code questions. The phrase 'Runs synchronously' implicitly distinguishes it from the asynchronous agent-job siblings (like dispatch_gemini_agent and check_agent_job), but it does not name any sibling explicitly, keeping it from a 5.

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?

Implies usage context (architectural or code questions across files) and notes synchronous execution, which hints at when to prefer it over async agent dispatch. However, it offers no explicit when-to-use/when-not guidance or named alternatives, leaving the agent to infer.

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 present, the description carries the full behavioral burden and discloses almost nothing: no ordering (most recent first?), no pagination/limit behavior, no scope of jobs, and no indication of what a job entry contains. The only real signal is that all statuses are returned, which contradicts the tool name's implication of actives-only.

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 compact sentence with no filler, front-loaded with the verb and resource. It is efficient, though the status enumeration carries most of the weight and could be paired with one clause on scope.

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 single-parameter list tool with no output schema, the definition covers purpose but omits ordering, scope, and result shape, leaving the agent to guess what a returned job record looks like. Adequate but clearly thin.

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 single 'limit' parameter is fully described in the schema ('Maximum number of recent jobs to return'), so the schema does the work. The description adds no ordering or default-value context beyond it, which is the baseline expectation at 100% coverage.

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 clear verb ('List') and resource ('subagent jobs') and usefully enumerates the statuses returned, which corrects the misleading 'active' in the name. It does not, however, distinguish itself from sibling check_agent_job or explain scope (own jobs vs all jobs).

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?

There is no guidance on when to use this rather than check_agent_job (single job status) or the dispatch tools. The reader must infer that this is the enumeration counterpart, but nothing in the text says so.

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 behavioral burden. It usefully signals that results are session-scoped and dynamic ('live', 'currently available'), but says nothing about what the listing returns (names vs. full metadata), whether it is cached, or any failure mode when no session is connected. Adequate but incomplete for a tool with zero annotation coverage and 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, zero waste, with the resource and scope front-loaded and the usage condition following. 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 zero-parameter list tool, purpose and the routing rule to dispatch_gemini_agent are covered. The only gap is the return shape, which matters slightly more here because no output schema exists to describe it.

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 no parameters, so there is nothing for the description to disambiguate and the schema is trivially complete. Baseline 4 applies for a zero-parameter tool.

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 (live models available from the connected Antigravity IDE session), and scopes it to the current session rather than a static catalogue. It also names the downstream consumer, dispatch_gemini_agent, so an agent can place it among its siblings.

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 call condition: invoke before dispatch_gemini_agent when the exact, currently-live model name is unknown. That is a concrete when-to-use trigger tied to a named sibling, leaving little to inference.

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