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

Annotations only say this is a non-read-only, non-idempotent, open-world write; the description goes far beyond them by disclosing daily polling cadence, per-Pin SmartPin credit consumption by design tier, that Pins arrive as unscheduled drafts, that a baseline snapshot suppresses existing posts, that duplicate feeds return a conflict, and that disconnected accounts are rejected. It also notes connecting itself costs no credits, which resolves the most likely user objection.

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-loads the purpose and the ongoing-automation framing before cost and edge cases, and nearly every sentence carries decision-relevant information. It runs long (roughly eleven sentences) and folds cost, baseline, and error behavior together without structural signposting, which makes it slower to scan than it needs to be.

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 an output schema, full parameter descriptions, and annotations, the description supplies exactly the behavioral context structured fields cannot express: recurring credit cost, draft status, baseline snapshot, conflict and disconnected-account failure modes. Nothing an agent needs before calling 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 100%, so the baseline is 3, but the description adds real semantics: feedUrl must be a genuine feed URL with preview_feed as the fallback, accountId must be a currently connected account because a disconnected one fails silently, and the account choice must be confirmed with the user. It leaves designTier, premiumStyle, autoRegenerate, and generationFrequency entirely to the schema.

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 — subscribes to a feed and assigns its generated Pins to one Pinterest account — and immediately disambiguates it from one-time imports and from the preview/update siblings. An agent can distinguish it from connect_pinterest_account, generate_pins_from_url, and update_feed without opening any 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?

Gives the triggering condition (user wants automatic Pin creation from a blog/RSS feed), an explicit non-use case (not a one-time import), a routing rule to preview_feed when only a site URL is available, and a pre-call clarification step with list_accounts when multiple accounts exist. Exclusions and alternatives are both named.

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