prepare_activity_publication

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

Adds meaningful behavior beyond the annotations: the two-phase draft/execute flow, that a draft has no action reference, that historical kilogram suggestions are read-only, and that audience and WOD TV settings are pulled from account preferences and rechecked before execution. None of this is inferable from readOnlyHint/openWorldHint, and nothing contradicts them.

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 single dense paragraph is front-loaded with the core action, but sentences are long and stack multiple conditions (draft mode, load confirmation, preference recheck, preview/confirm) without structure. Every clause carries information, yet a bulleted or sequenced layout would cost less effort to parse.

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?

An output schema exists, so return values need no explanation, and the description covers the workflow, preconditions, and confirmation gate sufficiently to call the tool correctly. The remaining shortfall is the undocumented parameters, which is a schema/description gap rather than a missing concept.

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% across 7 parameters, so the description is the only guidance and it covers only part of the surface: sourceActivityId (source ID), variantLabel (difficulty label), actualLoads (actual kilograms), and blockResults ('supported result'). gymId, comment, activityDate, and the sourceAlternative enum are never explained, leaving a real documentation gap.

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+resource: reads a selected gym workout in the current publication view and prepares one own activity entry, and names the upstream source (get_published_workouts). It distinguishes itself from execute_activity_publication through the 'prepare' framing and the confirmation gate, though the phrasing ('own activity entry', 'supported publication view') is dense enough that the exact artifact being produced takes a second read.

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?

Gives real when-to-use guidance: supply the source ID from get_published_workouts, resolve the difficulty label when several variants exist, and re-run the call with a supported result or explicitly confirmed kilograms when the first pass returns a draft. It does not explicitly name execute_activity_publication as the tool that consumes the prepared draft, so the hand-off is implied rather than stated.

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