push_artifact

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

The description explicitly states a write operation ('write edited fields back' and 'Overwrites the listed fields') while annotations declare readOnlyHint=true, which means the tool is supposedly read-only. This is a direct annotation contradiction, so the score must be 1 per the rules.

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?

The description is two sentences, front-loaded with the purpose, and every clause adds value (write action, prerequisites, no-merge behavior, conflict detection). 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?

The description covers prerequisites, core behavior, conflict handling, and parameter usage, but the annotation contradiction leaves side effects ambiguous. It also omits the return value or error behavior, and with no output schema, the agent is left without a complete picture.

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 100%, so all parameters are already documented. The description restates the dual-mode behavior of 'fields' and the conflict-abort purpose of 'expected_updated_on', but does not add significant new meaning beyond the schema, warranting the baseline score of 3.

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 opens with 'Local sync: write edited fields back to an artifact', which clearly states a specific verb ('write') and resource ('artifact'). It distinguishes itself from siblings like pull_artifact by referencing 'pulled files' and 'sync_status', making the purpose unambiguous.

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?

Explicit guidance is provided: 'requires WRITE_ENABLED=true', 'run sync_status first', and 'pass expected_updated_on to abort' if the record changed. It also explains the two modes of parameter passing (inline fields vs on-disk files), leaving no doubt when and how to use the tool.

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