Bibliography (Read Citation Cache)

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

Discloses key behavioral traits: no network calls, op=export writes .bib file and returns text, op=cited_by needs prior cache_cited_by. No annotations to contradict; description carries full burden effectively.

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 sentences, front-loaded with purpose, then precise per-operation details. Zero wasted words, every clause adds value.

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 multi-operation tool with 6 params and no output schema, description covers main returns (export returns bib text) and usage constraints. Lacks description of return format for get/list, but schema enums and defaults partially compensate.

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 83%, so description adds limited new meaning beyond enum values. However, it clarifies that op=export writes to outputPath and defaults to cacheDir/projectName.bib, and that op=cited_by require citeKey after cache_cited_by. Minor added value.

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?

Description clearly states it reads from local citation cache without network calls, and enumerates four distinct operations (get, list, export, cited_by). This distinguishes it from siblings like cache_cited_by which populates the cache.

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?

Explicitly tells when each operation is appropriate (e.g., op=get for one citation by key/AGLC4/neutral/title, op=list default, op=export writes BibLaTeX, op=cited_by requires prior cache_cited_by). Lacks explicit 'when not to use' but contextually clear.

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