chrysalide_start_task

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 that the call returns immediately with a job_id (valuable), but does not disclose that the task runs asynchronously in the background, that follow-ups via chrysalide_get_status/get_report are necessary, that a sandbox/worktree is created (implied by worktree param), or any resource/side-effect implications. For a long-running async job launcher, 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?

Two short sentences, front-loaded with the core purpose. Zero waste. Could arguably add more behavioral detail, but as written it is efficient and readable.

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?

Despite high schema coverage, this is a complex async job launcher with 9 parameters, no output schema, and no annotations. The description doesn't explain the job lifecycle (that it runs in background, needs polled status, could be cancelled via sibling), return format beyond job_id, or relationship to the sibling workflow. For a tool initiating long-running work, more operational context is needed.

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 all 9 parameters. The description adds minimal parameter meaning beyond this — 'goal' and 'repo_path' are intuitive and reinforced, but nothing about the budget semantics, provider format, or constraints is elaborated in the description. Baseline 3 is appropriate since schema handles the load.

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 clearly states the verb (Démarre/démarre), the resource (nouveau job Chrysalide), and the key behavior (returns immediately with a job_id). It's clearly distinct from siblings which get status, reports, or cancel. While it doesn't name the siblings, the immediate-return behavior and job_id clearly differentiate it from what siblings do.

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 usage context ('Démarre un nouveau job') and the immediate-return behavior implicitly tells the agent not to wait for results, but it doesn't explicitly state when to use this vs alternatives, nor does it mention that follow-up status/report calls would be needed. There's no explicit when/when-not guidance, only implied.

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