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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the safety profile is largely covered. The description still adds real context beyond them: an API Key is required, and it explicitly disclaims starting or retrying sampling, which matters for an agent deciding whether polling this endpoint will advance the task.

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?

Two tight sentences with the read action front-loaded and constraints following. Dense and largely waste-free, though the semicolon-clause stack makes the auth and timeout guidance feel appended rather than integrated.

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?

For a single-parameter read tool with no output schema, the description covers the essentials: what it returns (task plus financial state), auth requirement, and the absence of sampling side effects. Nothing an agent needs to call it correctly is missing.

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 description coverage is 0% for the single check_id parameter, so the description must carry the burden. It does partially, identifying it as a task ID and advising reuse of the original ID after a timeout, but it does not clarify the UUID format expectations or whether foreign check IDs error out.

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+resource: 'Read an owned observation task and its financial state,' and immediately bounds the scope with 'does not start or retry sampling.' This cleanly separates it from write-side siblings like geo_accept_observation and geo_cancel_observation.

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?

Provides one concrete usage rule ('use the original task ID after timeout before considering any new task'), which is genuinely useful polling guidance. However, it never names an alternative tool or states when NOT to use this one relative to the sibling set, so the routing guidance is implied rather than explicit.

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