spidra_account

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description adds real behavioral context beyond that — that credits.used includes credits held by still-running jobs, and that unused held credits are released when those jobs finish. That is non-obvious accounting behavior an agent would otherwise misread. It does not describe latency or error behavior, keeping it short of a 5.

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 what is returned, then when to call it, then bulleted parameter behavior, then a single caveat sentence about held credits. Every line carries distinct information and the bullet structure maps one-to-one onto the optional parameters.

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?

With no output schema, the description must carry the return-value burden, and it names the main fields (plan, credits left, bandwidth, monitor limit) plus the extra fields unlocked by the two flags. It stops short of enumerating the full response shape or units, but is sufficient for correct invocation.

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 would be 3, but the description adds meaning the schema lacks: 'usage' returns credits, requests and tokens per day (or per week for "weekly"), and 'byTool' returns credits per day split across scrape, crawl, search, parse and map. It also explains the interaction — byTool defaults to the last 7 days unless a usage range is supplied.

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?

The opening sentence names the exact resource returned: plan, credits remaining this billing period, Stealth Mode bandwidth, and monitor allowance. It is clearly distinguishable from every sibling (which are scrape/crawl/monitor actions) and an agent knows immediately this is the account/quota introspection tool.

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?

It gives explicit triggering conditions: 'Use it before a large batch, crawl or template run to check there's enough, or to answer "how many credits do I have"'. That ties it to specific sibling tools (spidra_batch_scrape, spidra_crawl, spidra_run_template). No exclusions are stated, but no sibling overlaps in purpose, so there is nothing to exclude.

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