update_citation

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

Annotations cover the safety profile (destructiveHint=true, idempotentHint=true), and the description adds genuinely new behavioral context: a citation holds ONE confidence shared by every attached fact, so re-grading propagates to all of them. That shared-state consequence is exactly the kind of side effect annotations cannot express.

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 IMPORTANT block is well front-loaded and the census example makes the rule concrete. The middle aphoristic sentence about page-less citations and per-instance confidence is opaque and only loosely actionable, costing some signal-to-noise.

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?

All five parameters are described in-text or in schema at 100% coverage, no output schema exists, and the annotations carry safety. The one gap is that no return/confirmation behavior is described, but for a straightforward in-place edit that is minor.

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 coverage is 100%, so the baseline is 3, but the description goes further by framing the page/confidence distinction ('a page-less citation is not a locator', 'confidence is a per-instance judgement, not a property of the source class'), which shapes how an agent should choose values.

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 opening sentence gives a specific verb (Edit) plus the exact editable resources (locator, confidence, date, source pointer), which is enough to separate it from add_citation/get_citation. It does not, however, explicitly contrast itself with the closely related siblings update_source or the generic update_object_fields, so the differentiation is implicit rather than stated.

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 IMPORTANT paragraph gives real usage guidance for one decision: when the same page supports a second claim, add a new citation instead of re-grading. That is valuable, but it is a narrow in-tool rule; there is no guidance on when to reach for update_citation versus add_citation, uncite, or update_source.

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