update_citations

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

Annotations already declare destructive/idempotent, but the description adds behavior the annotations cannot convey: per-row independent writes and transactions (no cross-row atomicity), optimistic concurrency via expect_page_prefix, and the full outcome vocabulary (applied, unchanged, drifted, missing, error). This is consistent with destructiveHint=true and idempotentHint=true.

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?

Four short sentences, zero padding, with the core purpose front-loaded before the transactional and drift details. Every sentence carries distinct information.

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, and the description compensates by enumerating the per-row result statuses, which is exactly what an agent needs to interpret a sweep response. Combined with the drift rule and per-row transaction semantics, nothing material is missing for this mutation 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% and the nested CitationEdit definitions already explain page, confidence and expect_page_prefix in detail. The description's mention of 'pages or confidences' and the drift contract largely restates the schema, 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 (re-write), resource (citations' pages/confidences) and scope (many, in one call -- a sweep). It also explicitly distinguishes itself from the sibling update_citation by defining each row as that operation, so an agent can pick batch vs single without opening schemas.

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 batch framing plus 'Each row is update_citation' clearly signals when this tool is appropriate versus the single-record sibling. It stops short of an explicit when-not/exclusion statement (e.g., prefer update_citation for a single edit), so it is not a full 5.

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