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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed world, so the safety profile requires no description support. The description adds the shape of the payload (status plus per-prompt/per-engine rows) but nothing about volume, pagination, or behavior when a run is still in progress — the last of which matters for a status-bearing tool.

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?

A single dense sentence with no padding, front-loading the resource and then the returned fields. It is efficiently sized; the only quibble is that the field list slightly duplicates the output schema.

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 simple one-parameter read tool with an output schema and full annotations, the description covers what is returned and requires nothing more. It is only missing a note on incomplete runs, which is a modest gap rather than a blocking one.

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?

With one parameter at 100% schema coverage, the schema already explains run_id and even points to run_citation_tracker as its source. The description contributes no additional meaning about the identifier format or lookup behavior.

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 names a specific resource (a citation run) and enumerates its contents: status plus per-prompt, per-engine results with mentioned/cited/position/snippet. An agent can tell this is a retrieval tool for a single run rather than a tracker listing, though it does not explicitly contrast itself with siblings such as get_citation_tracker.

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?

There is no statement of when to call this versus run_citation_tracker, get_citation_tracker, or citation_tracker_history. Usage is only implied by the word 'run' and by the schema note that run_id comes from run_citation_tracker.

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