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

Annotations only declare not read-only and not destructive. The description adds substantial behavioral context: remove is a soft-delete, scheduled dates resolve in the tenant's timezone at the default publish time, approval_mode=email is the only accepted mode with auto/warning refused while auto-publishing is off, and approved drafts require an explicit publish_draft call. This goes well beyond the structured annotations.

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?

Roughly 100 words, dense but efficient. The action dispatch is front-loaded and each clause earns its place; the approval_mode caveat, critical for correct invocation, is clearly stated. Slightly heavy for a tool definition, but no filler or repetition of schema content.

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 15-parameter, 4-mode mutation tool with no output schema, the description covers action semantics, hard constraints, soft-delete behavior, and publish routing. Gaps remain: it doesn't map which parameters are required per action (draft_id for update/remove lives only in the schema) and doesn't describe error cases, but the critical correctness constraints are all present.

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 only 40%, so the description carries meaning for the most consequential parameters: the action enum's four values and their effects, approval_mode's hard constraint, scheduled_date's timezone/default-time semantics, slides' 2-10 limit, and days meaning 'next N days'. A few params (beat_slug, source_asset_id, caption_mode vs user_caption) still lack semantic explanation beyond the schema, so it doesn't fully compensate.

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?

Title and description both use specific verbs plus a clear resource: 'Add / update / remove scheduled posts' and 'Manage scheduled posts'. The description enumerates four distinct action modes (add, update, remove, bulk_fill) with precise semantics for each, and distinguishes itself from the sibling publish_draft by stating that publishing is a separate explicit call.

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 description gives clear context for when to use the tool (managing scheduled posts) and explicitly routes the publishing step away to the sibling tool publish_draft, noting the owner's app tap as the alternative. It does not cover sibling routing for reading schedules (get_schedule) or one-off AI generation (generate_draft), so exclusion guidance is only partial.

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