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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false, openWorldHint false), and the description adds substantial behavioral context on top: the CITED vs RETRIEVED-only split, how legacy runs lacking the split are quarantined rather than blended, Gemini's site-not-page behavior, and that null categories are 'never guessed'. This is unusually rich disclosure of edge-case semantics.

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?

The opening sentence is well front-loaded, but the rest is a single sprawling paragraph with deeply nested parentheticals (shareOfChats, category sources) that is hard to parse and far longer than needed. Density substitutes for structure here.

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?

There is no output schema, so the description must carry the return-value burden, and it does: per-domain run counts, top pages, shareOfChats and its formula, and category/categorySource. It is nearly complete, with only minor gaps (no mention of pagination or result limits).

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 the schema already documents all five parameters (days, model, clientId, promptId, projectId), establishing the baseline of 3. The description adds a little framing (window semantics, engine filter behavior) but nothing the schema does not already convey.

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 and resource ('which domains AI engines cite when answering this project's prompts') and scopes it to a window, which is far more precise than a restated name. It does not, however, explicitly differentiate itself from closely-named siblings like get_cited_url or list_citation_lifetimes, leaving the agent to infer the boundary.

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 description explains what is returned in great detail but never says when to reach for this tool versus the sibling citation tools (get_cited_url, list_citation_lifetimes, get_ai_attribution). There is no when/when-not framing or named alternative, so selection guidance is absent.

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