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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the bar is lower, yet the description still adds real value: no provider or browser call and no scan allowance consumed, 'missing or failed evidence remains unavailable, not zero' (an important semantic that prevents misreading absent data), and a prompt-injection warning that quoted source text is untrusted. Those are behaviors not visible in the annotations.

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?

Five short, front-loaded sentences with no filler; the operational constraint (no scan allowance consumed) comes first. The opening sentence is a pure restatement of the title and earns little, which keeps this just below a 5.

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 carries the burden of describing the return value, but it never says what a 'citation source' record contains or how results are shaped. It does cover cost, cache semantics, missing-data behavior, and data trust, which is solid for a zero-parameter read tool, but the return-shape gap is real.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate and it correctly adds no parameter discussion.

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 opens by restating the title ('Saved citation sources') and never supplies a verb or a clear statement of what is returned — presumably the sources that AI answers cite. It is distinguishable from most siblings only by inference, and no sibling (e.g. get_source_profile, get_cited_queries) is named or contrasted.

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?

'Reads saved measurements or existing caches only' implies this is the no-cost read path and that it requires pre-existing data, which is useful usage context. However, it never states when to choose this over request_rescan or how to obtain data when the cache is empty, leaving the alternative-selection decision implicit.

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