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

With no annotations, the description carries the full burden and does so: it discloses returned fields per view, the edge case that extra purchased/granted credits make `remainingCredits` exceed `planCredits`, that billing-period dates and the newest `endDate` may be null, that the endpoint split double-counts search usage, and that a `notice` means requested splits/daily periods are unavailable. These are exactly the non-obvious behaviors an agent needs before trusting the numbers.

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?

Purpose and the two-view decision rule are front-loaded, and each subsequent paragraph maps to a distinct concern (current view, historical view, limitations). It is dense but long for a 4-parameter tool; the detailed field-level return narration is justified only because no output schema exists, though some enumeration of field names could be trimmed.

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?

No output schema exists, so the description must explain returns — and it does, per view, including nullability, sort order, and the `notice` fallback. It also closes the biggest likely misinterpretation (attributing credits to individual jobs) by pointing to per-tool `creditsUsed` and the dashboard, leaving nothing an agent needs missing before calling it.

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; the description goes beyond it by explaining what each split actually means semantically (byEndpoint splits by scrape/search/crawl/map/agent and includes search usage the unsplit and per-key figures omit; byApiKey splits per API key) and by documenting the default monthly binning vs UTC daily periods. The view-selection interactions are mostly restated from the schema rather than added, keeping this just below the top score.

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 ('Get the authenticated Firecrawl team's current credit balance or its credit usage over the last 90 days') and immediately partitions the tool into two named views, so an agent knows exactly what it retrieves. It also scopes itself against adjacent surfaces (dashboard Usage/Logs pages, per-tool `creditsUsed`), which separates it from firecrawl_usage_dashboard and the per-call tools.

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 routing is given per view: 'Use the current view to answer how many credits remain or to check billing-period boundaries. Use the historical view to answer what credits were spent on and when.' It further names the alternatives for attribution ('Each tool's own result reports what that call used... the Usage and Logs pages of the Firecrawl dashboard list usage per job'), including a clear when-not ('cannot attribute credits to individual jobs, URLs, or MCP clients').

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