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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral value beyond that: it discloses the edge-case rule that an engine failing to answer is skipped rather than recorded as 'not cited', and that results reflect the latest measurement rather than history.

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 no filler; the enumeration of returned fields comes first and the non-obvious skip behavior is front-loaded in a second, separate sentence. Nothing here is wasted.

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?

An output schema exists, so the description correctly does not spend words explaining return values. For a simple 2-parameter read tool this is nearly complete; the only shortfall is the missing routing hint relative to run_citation_check and get_share_of_voice.

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 100%, so both domain_id and limit are already documented in the schema, including the 'from list_domains' provenance and the 1-500 bound. The description adds nothing about parameter tuning (e.g., what limit does to pagination of questions/engines), so the baseline 3 applies.

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 ('show') and resource (latest citation measurement per tracked question and AI engine) and even enumerates the returned fields: cited status, position, URLs, timestamp. It is clear what the tool does, but it never names the sibling that would trigger a fresh measurement (run_citation_check), so the boundary is inferable rather than explicit.

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?

The phrase 'latest real measurement' implies this is the read-only reporting path rather than a trigger, which is the right usage context. However, there is no explicit statement of when to call this versus run_citation_check or check_citation_readiness, and no prerequisites are given.

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