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

Annotations already declare readOnly/openWorld/non-destructive, but the description adds substantial context beyond them: per-call credit range of 1–60, 'a failed call costs 0', and that handle re-reads are free. It also tells the agent to follow error.fix on failure and surface billing.display, which is behavior no annotation conveys.

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 core purpose and the sibling routing rule, then operational caveats. Slightly dense and telegraphic, and the per-platform op counts are the kind of enumeration that ages quickly, but every line carries a usable instruction.

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 still leaks the response shape the agent needs — page.cursor for pagination, request_id/handle for free re-reads, error.fix for remediation, billing.display for user-facing cost. Missing only an explicit statement of what a successful result contains.

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 meaning: the 1–60 credit range that max_cost_credits guards against, the requirement to pass links whole as given, and how cursor/handle compose with an unchanged argument set. It stops short of explaining the shape of 'params', which is inherently op-specific.

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 ('Call one platform-specific capability by its op') and explicitly contrasts itself with two siblings, find and capabilities. The only friction is the unexplained reference to 'the six actions', which an agent must infer from the sibling list rather than read here.

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 an explicit when-to-use condition ('what the six actions do not cover'), names the two routing alternatives (find to locate an op, capabilities to enumerate ops with parameters and cost), and adds operational rules for links, error handling, and billing disclosure. Nothing is left to inference.

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