format_bibliography

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

The description states 'Read-only and idempotent' and explains deterministic behavior: 'Entries are de-duplicated by URL and ordered deterministically, so the same inputs always produce byte-identical output (no network, no timestamps).' This adds valuable context beyond the annotations, which already declare readOnlyHint, destructiveHint, and idempotentHint.

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 comprehensive, with a logical flow: purpose first, then style formats, input methods, behavioral guarantees, and references to sibling tools. Every sentence adds essential information without redundancy.

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 moderate complexity (3 parameters, output schema exists), the description covers input methods, style options, de-duplication, determinism, and use cases. It explains the DOI field's role in interoperability with reference managers and provides clear guidance on alternatives. The output is described as a string plus entry count, which aligns with the output schema.

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%, but the description adds significant meaning: it explains that 'apa/mla are human-readable; bibtex/ris/csl-json are reference-manager interchange formats' and advises to 'pass their doi so the persistent id survives' for sources. It also suggests using results from academic_search or citation_graph, enhancing the schema's built-in descriptions.

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 'Turn a set of sources into a formatted bibliography' and specifies the supported styles (apa, mla, bibtex, ris, csl-json). It distinguishes itself from sibling tools like research_export and verify_citation by noting their different purposes, making the tool's role unmistakable.

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 explicitly tells when to use this tool ('builds the citations section') and when to use alternatives: 'Use research_export for the full narrative report and verify_citation to confirm a citation before you rely on it.' It also guides how to provide sources, like passing doi from academic_search or citation_graph.

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