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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description adds meaningful behavioral context beyond those flags: no authentication, deterministic comparison, no input storage, no document fetching, and the exact nature of returned data (counts, normalized entries, duplicate groups with zero-based indices). It also clarifies limits (does not establish truth) without contradicting any annotation.

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 sentences with no filler; every sentence contributes a distinct fact: purpose, operational behavior, return contents, and a boundary with alternative tool. The main purpose is front-loaded in the first sentence, and the caveat is placed at the end for clear emphasis.

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, read-only, idempotent tool with a detailed schema and rich annotations, the description is complete. It states inputs, behavior, output type, and limitations, and it references the correct sibling for deeper verification, so an agent has all needed context to call it appropriately.

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 baseline is 3. The tool description mentions citation types and output indexing, but the input schema already documents allowed source types, length limits, order-dependent indices, arXiv version distinctness, and unrecognized-entry handling. The description does not add significant new parameter-level meaning beyond the schema.

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 with a specific verb and resource: 'Deduplicate supplied DOI, arXiv and URL citations.' It clearly positions the tool as a pre-review deduplication step and differentiates it from the substantive-review sibling task_action by stating it 'does not establish truth or source independence.'

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 tells the agent when to use the tool ('before reviewing evidence') and when not to rely on it: 'Does not establish truth or source independence; use task_action verifications for a substantive review.' This is an explicit alternative and exclusion, leaving no ambiguity about the tool's role.

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