compute.push_project

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

With only readOnlyHint=false supplied, the description carries most of the burden and does so well: it discloses the dry-run default, that deletion is never performed, and that newer target files are protected unless force=true. The remaining gap is the `data` switch, whose effect on what is copied is never explained.

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, each doing distinct work: what it does, how the plan/apply cycle works, and what safety guarantees apply. The most decision-relevant fact (dry-run default) is front-loaded in the second sentence.

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 mutating, six-parameter transfer tool with no output schema and no annotations beyond readOnlyHint, the description covers the safety model and apply semantics but leaves two parameters and the return shape of the planning phase unexplained. An agent could call it correctly in the default case but would be guessing on `data` and `from_node`.

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 for all six parameters. It covers only `confirm` and `force`; `data` and `from_node` — the two non-obvious parameters — are left entirely undefined, and an agent cannot infer from the schema or the prose what they change about the operation.

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: 'Copy a project checkout to a node, sending only the files that differ' — an agent immediately knows this is an incremental push of project content to a node. It does not, however, distinguish itself from the sibling compute_sync_project, which reads as a near-identical operation.

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 plan/apply contract is spelled out ('Plans by default; confirm=true applies'), which is genuinely useful invocation guidance and prevents accidental writes. There is no guidance on when to prefer this over compute_sync_project, compute_collect_results, or other transfer-adjacent siblings, and no stated prerequisites such as node reachability.

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