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

Annotations only say readOnly=false, idempotent=false, openWorld=true; the description goes far beyond by disclosing that the call is asynchronous, metered with per-tier credit costs (~3/~7/~1, resolved server-side), takes 1-3 minutes, and charges the user. It also explains the deduplication nuance — in-flight repeats return the SAME generation with deduplicated: true and cost nothing, while post-completion repeats start and bill a NEW generation — which clarifies rather than contradicts idempotentHint=false.

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 'use this when' trigger, then ordered by operational need: cost, latency, polling, dedup, account selection. Dense but almost every clause carries a distinct operational fact; the parenthetical credit breakdown is the only mildly redundant part.

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?

Covers the full async lifecycle an agent needs: prerequisites, cost, latency, polling target, where results surface (list_posts with matching generationId), and the retry hazard. An output schema exists, so return-value detail is correctly omitted.

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 url, title, keywords, accountId, designTier and premiumStyle. The description adds only the accountId provenance (list_accounts) and reiterates tier credit costs already present in the schema; keywords and title get no narrative treatment. Baseline 3.

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?

Opens with a specific verb+resource+scope: 'create Pin drafts in Tailwind from a web page (blog post, product page, or article URL).' This cleanly separates it from generate_pin_copy (copy only) and create_post (single post creation) without needing the 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 strong prerequisites (accountId from list_accounts, ask the user when multiple accounts exist, don't pick for them) and a retry protocol (poll get_generation_status before repeating). It stops short of an explicit 'use X instead when...' contrast against similarly named siblings like generate_pin_copy or regenerate_pin_design.

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