phabricator_revision_inline_publish

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

Annotations already declare destructiveHint=true and readOnlyHint=false. The description adds critical behavioral details beyond that: it publishes pending 'Done' changes as a side effect, requires 'Can Edit' permission and the differential.inline.* extension, and warns that retrying a timed-out call may fail because already-published inline IDs are rejected.

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?

Front-loaded with the primary action, then efficiently covers side effects, default scope, prerequisites, and failure handling. Every sentence adds value without 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?

Given the tool's complexity (mutation with side effects), annotations already cover destructive behavior, and the description fills in permissions, side effects, scope of the operation, and retry semantics. No output schema exists, but for a publish action the return is simple success/failure and the description is sufficient for correct invocation.

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 the schema already documents all three parameters. The description adds extra meaning to inlineIDs by clarifying that omitting it publishes 'EVERY draft you have on the revision, including ones started in a browser', which is not fully captured in the schema's description.

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 ('Publish') and resource ('draft inline comments on a Differential revision'), and clarifies the exact equivalent action ('pressing Submit in the web UI'). This distinguishes it from sibling tools like phabricator_revision_inline_comment (create draft) and phabricator_revision_inline_done (mark done).

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?

Explains default behavior ('Without inlineIDs, EVERY draft... is published'), notes side effects ('Also publishes pending Done changes'), and gives a retry guideline ('If a call times out, search before retrying'). Does not explicitly name an alternative tool for selective publishing, but the context is clear enough to guide usage.

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