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

With no annotations supplied, the description carries the full behavioral burden and does meaningful work: it discloses that conflicts are reported with no partial change (atomicity), that no commit is created, and that discard=true destroys the job's worktree and branch. It stops short of covering permissions or whether a successful apply can be repeated safely.

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, front-loaded with the primary behavior and the git primitive, then the failure mode, then the destructive alternative. No filler or redundancy.

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 mutation tool with no annotations and no output schema, the description covers the core semantics, the no-op-on-conflict guarantee, and the destructive discard path. Only the shape of what gets reported on conflict is left unstated, which is modest given the tool's simplicity.

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 does for the non-obvious parameter by explaining exactly what discard=true does (drops the worktree and branch) rather than leaving a bare boolean. job_id's meaning is only inferable from "a finished job's changes," which is a minor remaining 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 names a specific verb-and-resource pair ("Stage a finished job's changes in the main checkout") and pins down the mechanism with "git merge --squash, no commit." It does not explicitly name a sibling like vibe_result or vibe_wait, but "finished job" implicitly frames the ordering relative to those 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?

"A finished job's" signals the precondition that the job must have completed, which implies when this tool is appropriate. The discard branch is described as an alternative behavior, but neither branch states when an agent should choose apply versus simply reading the result with vibe_result.

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 and does disclose two useful facts: the operation is a mutation that terminates running work, and the worktree survives. It does not say whether a running job is killed gracefully, what permissions are needed, whether the call is idempotent, or whether an error is returned for already-completed jobs.

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, zero filler, and the state distinction is front-loaded before the artifact-preservation detail. Nothing is repeated and nothing is padded.

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 mutation with no annotations and no output schema, the description covers the core action and one side effect, but leaves the agent guessing about the return value, failure modes, and id provenance. It is adequate to call the tool but not 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?

There is a single required job_id parameter with 0% schema description coverage, so the description must compensate and largely does not: it never says where job_id comes from (presumably vibe_submit), what format it takes, or how an invalid or unknown id is handled. It only implies that the id must refer to a queued or running job.

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 pair (cancel/kill) and the resource (a queued or running job), and its state-dependent framing makes the tool's scope immediately clear. It does not reference any sibling, but none of vibe_submit, vibe_wait, vibe_result or vibe_apply overlaps with cancellation, so disambiguation is effectively implicit rather than stated.

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 phrase 'a queued job' versus 'a running one' tells an agent the two contexts in which to call it and what happens in each. It stops short of exclusions or follow-up guidance, such as whether to read results via vibe_result afterwards or what to do if the job has already finished.

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 load and does disclose real behavioral traits: the summary is explicitly 'unverified' (a trust caveat) and the diff is 'capped' when diff=true (a size limit). It omits error behavior when job_id is unknown or the job is incomplete, which keeps it below a 5.

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 dense sentence with the returned payload front-loaded and the diff flag explained last; there is no redundant or filler text.

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 must describe the return value, and it enumerates the returned fields plus the optional diff. Complete enough to call correctly, with only edge-case/error behavior and sibling routing left unaddressed.

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 0%, so the description must compensate, and it does for the key optional flag: 'diff=true appends the diff (capped)' explains both effect and limit. job_id is only implicitly defined as identifying the job, leaving one parameter thinly covered.

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 resource ('Outcome of a job') and enumerates exactly what the outcome contains: summary, diffstat, added files, scope violations, tokens, cost. That is far more concrete than the bare name, though it never explicitly names how it differs from siblings like vibe_wait or vibe_apply.

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 only implied: you call this to retrieve a job's outcome, presumably after it completes, but the description never says whether it works on a still-running job or how it relates to vibe_wait/vibe_apply. There are no explicit when-not conditions.

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 supplied, so the description carries the burden and it does cover the important traits: isolated worktree execution, immediate return rather than blocking, and concurrency serialization when scopes overlap (omit = whole repo). It does not state cost implications despite mentioning a 'cheaper model', nor what happens on failure, timeout, or cancellation, and never says what value is returned for handing to vibe_wait.

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?

Tight and front-loaded: the purpose leads, the parameter glosses follow, and the workflow hand-off is one short line at the end. The telegraphic 'name: meaning' fragments are efficient but border on cryptic for the skill and scope lines, which cost it a point.

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?

This is an 8-parameter mutating/queueing tool with no annotations, no output schema, and 0% schema coverage, so the description must do nearly all the work. It covers the core mental model and next steps well, but omits the four budget/limit parameters and does not say that submission returns a job identifier — a real gap given that vibe_wait, vibe_result, and vibe_apply presumably need that ID.

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% across 8 parameters, so the description is the only source of parameter meaning — and it only explains four of them (spec, skill, scope, base_job). Useful semantics are added for those (where the skill file lives, scope overlap behavior, building on a prior job), but title, max_price, max_turns, and time_limit get nothing beyond self-describing names, leaving half the surface un-elaborated.

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 first sentence gives a specific verb and resource — 'Queue a coding task for Mistral Vibe ... in an isolated git worktree' — naming the executor and the isolation model. It is clearly separable from siblings because the closing line maps the whole follow-up lifecycle (vibe_wait, vibe_result, vibe_apply) and leaves vibe_submit as the entry point. An agent can pick it out without opening a 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?

Usage context is clear: this is the asynchronous delegation path, and the spec guidance ('complete and self-contained; Vibe sees neither this chat nor project docs') tells the agent how to use it correctly. It also directs follow-up to the specific sibling tools in order. It stops short of stating when NOT to delegate or what to do instead (e.g., doing the edit inline), so it is not a full 5.

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 burden. It usefully discloses the blocking nature, the default scope, the timeout=0 special case, and that output is one line per job. It does not say what happens when the timeout expires before any job ends (error vs partial result), which is the key behavioral ambiguity for a wait 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?

Three short sentences, front-loaded with the core semantics (blocking wait, scope, timeout) before the defaults and output note. No redundant or filler wording; every clause conveys 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?

For a 3-parameter, zero-required, annotation-free tool with no output schema, the description covers defaults, special values, and the shape of the return ('one line per job'). The main remaining gap is the outcome when the timeout elapses, which an agent needs in order to handle the result 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 0%, so the description must compensate, and it does: job_ids is explained with its default of all active jobs, timeout is explained as a bound with a documented timeout=0 status-only mode, and wait_all is defined as every-vs-any. Only the unit/format of timeout and the expected id format are left unstated.

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 ('Wait until ... job[s] ... ends') and clarifies the scope of the wait (any job, or every job when wait_all is set). It does not explicitly distinguish itself from the sibling vibe_result, which an agent could reasonably confuse with a blocking wait, so it falls short of 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?

Useful context is given implicitly: default job_ids covers all active jobs, and timeout=0 is a pure status check rather than a wait. However, there is no explicit statement of when to prefer vibe_wait over vibe_result or vibe_submit, so the agent must infer the choice from sibling names.

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