Account link status

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds real context the annotations cannot: it needs no API key, it is free of credit cost, and it distinguishes 'linked (and where it came from)' from 'pending (with the link and code to show the user)' — the latter telling the agent to surface the code to a human. It stops short of describing polling cadence or latency, which is the only notable gap.

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?

Three labeled sentences — what it reports, when to use it, cost — with nothing extraneous. The state enumeration is front-loaded so the agent reads the most decision-relevant information first, and the 'Credits: free, no credits' line is short enough to justify its presence.

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 an output schema present, the description is not obliged to explain return shapes, and annotations carry the safety profile, so what remains — trigger condition, key-free operation, cost — is all covered. Only polling/repeat-call behavior (how often to re-check while pending) is left unaddressed for what is inherently a status-polling tool.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and it correctly spends no words on inputs (baseline 4 for a 0-param schema). The brief note that it needs no key is a useful related clarification rather than duplicated schema content.

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 description gives a specific verb and resource ('Reports whether this server has a Storeshot API key') and then enumerates the exact states it can return: linked, pending, expired, denied, failed, not started. That enumeration makes it unmistakable versus siblings like get_job_status or get_credits, which are about work and billing rather than authentication.

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 states an explicit trigger ('after another tool answered ACCOUNT_LINK_REQUIRED or ACCOUNT_LINK_PENDING, to check whether the user approved') and an explicit exclusion ('It never starts linking itself and needs no key'). An agent knows both when to call it and what it must not expect from it.

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