citation_graph

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

With annotations already declaring safe read-only/idempotent behavior, the description adds the single-hop limitation, provider-dependent enrichment (intent/influence flags), and a security note to treat results as external data, not instructions. These details go beyond the structured hints.

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 description is concise yet complete, front-loading the core purpose and then covering usage, behavior, and output. All sentences contribute meaningful information without fluff.

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?

Given the tool's complexity (6 params, multiple providers), the description covers purpose, usage scenario, behavioral limits, output type, and security guidance. The existence of an output schema means return values are already documented, so the description is sufficiently complete.

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. The description mentions 'when the provider supplies them (Semantic Scholar)' which overlaps with the schema's provider description, not adding new meaning. It does not elaborate on any parameters 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 clearly states the tool maps a paper's citation neighborhood with forward/backward directions, starting from a DOI or title. It distinguishes itself from siblings by referencing academic_search for discovery and scrape_page for reading PDFs, positioning itself as the citation-traversal tool.

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 explicitly says 'Use this for literature reviews and prior-art tracing' and pairs with academic_search and scrape_page. It also notes 'Single-hop per call (no recursive crawl)' to set expectations vs potential recursion. This provides clear guidance on when and how to use the tool.

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