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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered structurally. The description adds genuinely non-obvious behavior: failed/missing units are preserved, the API measurement scope is retained, absence must not be read as a negative mention, and no new sampling occurs.

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 compact sentences: the core read action and scope come first, followed by the interpretation guardrails and the auth/no-sampling note. No filler, though the 'do not invent answers' clause is more agent-steering than tool description.

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 read-only, annotated tool with no output schema this is mostly adequate — it conveys that a page of units is returned with failed/missing entries intact. It is thin on pagination behavior (how to advance via cursor, what the page contains) and does not clarify parameter usage, which is the main residual gap.

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% across three parameters, so the description carries the burden — but it only gestures at paging ('a page') and ownership ('owned observation'). It never explains limit bounds, cursor semantics, or that check_id is the required UUID identifier, leaving the schema's raw types to do the work.

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 ('Read a page of actual answer units from an owned observation') with clear paging/ownership scope. It distinguishes itself reasonably from geo_get_observation and geo_get_sources by resource type, though it never explicitly names or contrasts a sibling.

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?

'Requires API Key; no new sampling' plus 'from an owned observation' imply this reads pre-existing measurement results rather than triggering collection, which is useful context. However, it never states when to use this versus geo_get_observation or geo_get_sources, so the routing guidance remains implicit.

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