compute.sync_project

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

readOnlyHint=false is the only annotation, and the description adds real context beyond it: the default call is a non-mutating preview, mutation requires confirm=true, and the tool self-guards against a dirty working tree. It stops short of saying what a checkout does to untracked files or what the response contains, but the safety profile is meaningfully clearer than the annotation alone.

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 tight sentence with the preview/apply distinction front-loaded and the safety constraint appended where it is easiest to act on. No filler or redundant restatement of the tool name.

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 mutation-capable tool with no output schema and zero schema coverage, the description covers the dry-run default and the dirty-tree refusal, which are the critical risks. It is still incomplete on the apply/confirm interaction and on what a successful or failed sync returns, so an agent could invoke it incorrectly on the first try.

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 carry all four parameters. It explains confirm and loosely implies project_id/node_id ('a project on one node'), but the 'apply' boolean is never mentioned, and the description's framing ('apply, with confirm=true') actively muddles whether apply or confirm is the real trigger. Two of four parameters remain ambiguous.

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 concrete verb and resource chain: show/apply a git fetch/checkout for a project on one node. That is far more specific than the name alone, and it distinguishes the read-only preview from the mutating mode. It does not differentiate from any sibling, though no sibling performs the same sync action.

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?

It gives the default behavior (show) and the condition to mutate (confirm=true), plus a refusal condition on a dirty working tree. But it never says when to prefer this over compute_push_project or compute_fetch_results, and it leaves the relationship between the separate 'apply' and 'confirm' boolean parameters undefined, which is the main usage question an agent has.

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