update_citations

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

Annotations declare destructive and non-readOnly, and the description adds real context: each row is its own write and transaction, drift protection via expect_page_prefix is described, and per-row outcomes (applied, unchanged, drifted, missing, error) are listed. It stops short of stating whether partial success is rolled back.

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?

Front-loaded purpose, then transactional behavior and outcome states. The '-- a sweep' aside and line-broken formatting are slightly wasteful but the content is tight overall.

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 single-parameter bulk mutation with no output schema, the description covers scope, concurrency semantics, drift protection and per-row result states. The main gap is partial-failure/rollback behavior, which matters for a destructive tool.

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 items, page, confidence and expect_page_prefix in detail. The description reinforces the drift semantics but adds no parameter meaning beyond the schema; baseline 3 fits.

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: re-writing pages or confidences on many citations in one call. It clearly differs from the singular sibling update_citation, but the phrase '-- a sweep' is informal filler rather than sharpening scope.

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 implies bulk use ('many', one call vs per-row writes) but never states when to prefer this over calling update_citation repeatedly, nor when not to use it. Context is inferable, not explicit.

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