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

Annotations already cover read-only, idempotent, open-world, non-destructive, so the description is free to spend its words on what annotations can't express: the upstream source is Crossref, the citing-works direction is unavailable, and the call surfaces BibTeX/RIS/CSV/PDF artifacts. A small gap remains around external-API cost or latency, but the disclosed source limitation is genuinely useful context.

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?

Two front-loaded sentences: the trigger and payload come first, the exclusions second. It is dense but every clause carries information; the trailing list of file formats and the 'no full text' note are borderline but still earn their place as scope boundaries.

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?

With an output schema present and full schema coverage, the description needn't explain return values, and it does supply the source, the directional limitation, and the sibling routing an agent needs. The one blemish is the inconsistency between 'the list of works that cite the paper is not available' and the limit parameter's promise of 'citing works', which could leave an agent unsure what limit actually controls.

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 both parameters are already documented and the baseline is 3. The description only reinforces that a single DOI is required; it adds no format or bounds detail for 'limit' beyond what the schema states, and it notably doesn't reconcile its 'citing works not available' claim with the schema's 'how many references and citing works to show'.

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 names a specific verb and resource (fetch the most-cited references plus citation count for one DOI) and frames the use case (backward snowballing). It explicitly distinguishes itself from find_papers by rejecting titles and topic search, so an agent can route between the two siblings without opening either schema.

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?

It states the triggering condition ('when the user has one paper (DOI)'), the exclusions ('does not accept titles or search by topic', 'does not read full text'), and names the alternative tool (find_papers) for the excluded case. This is the full when/when-not/alternative triad.

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