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

Annotations already declare non-read-only, non-idempotent, open-world, non-destructive, so the description's job is to add nuance — and it does: publishing is irreversible, publish_now only queues, and the result must be checked via list_posts. The only gap is that 'irreversible publishing' sits uneasily beside destructiveHint=false without reconciling that destructive refers to deletion, leaving a small ambiguity.

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 account-selection prerequisite, then the mode choice, then the irreversibility warning, then platform extras — a sensible priority order. Every sentence carries a constraint, though the platform-specific paragraph partially duplicates nested schema descriptions and could be trimmed without losing guidance.

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 12-parameter, deeply nested, non-idempotent mutation with no output schema, the description covers the account resolution path, mode exclusivity, irreversibility, return value (post_uid), and the four platform-specific sub-objects with their prerequisite lookups. Nothing an agent needs in order to call this correctly is missing.

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 92% so the baseline is 3, but the description adds genuine semantics the schema cannot express: the exactly-one-of constraint between scheduled_at and publish_now (there is no oneOf/top-level exclusivity in the schema), the rule that one platform settings object applies to every account of that platform, and that a YouTube post takes exactly one video. It repeats some nested-object descriptions already present in the schema, which keeps it off a 5.

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 ('Create a post on one or more connected social accounts') and immediately distinguishes itself from siblings by naming reschedule_post / cancel_post as the consumers of its return value and by describing its own create-and-schedule dual mode. An agent can separate this from update_post or list_posts without opening a schema.

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 prerequisites and exclusions: call list_social_accounts first, use only accounts with can_post: true, copy platform_slug verbatim, never guess. It gives the decision rule between the two modes ('when in doubt, schedule'), requires explicit user consent for publish_now, and adds per-platform preconditions (get_tiktok_creator_info, list_pinterest_boards) plus the Dev.to isolation constraint.

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