Bibliography (Read Citation Cache)

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

With no annotations, the description fully discloses the read-only nature ('without network calls') and explains each operation's behavior, including the side effect of writing a .bib file for 'export'. It does not mention any potential data mutability beyond that file write.

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 two sentences with no wasted words. The first sentence states the core purpose, and the second sentence enumerates the operations efficiently. It is front-loaded and easy to parse.

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 has 6 parameters and multiple operations, the description covers all operations and key parameters, including required fields for specific ops. No output schema is present, but return values are described sufficiently. It feels complete for an agent to understand usage.

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%, and the description adds context beyond the schema, e.g., specifying that 'query' is required for 'op=get' and that 'outputPath' defaults to a specific path. This helps the agent understand parameter usage beyond the enum and type definitions.

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 reads from a local citation cache without network calls, and enumerates specific operations (get, list, export, cited_by). This distinguishes it from sibling tools that involve network calls or different actions.

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 provides clear context for when to use each operation (e.g., 'get retrieves one citation by cite key...', 'list (default) lists cached citations'). However, it does not explicitly state when not to use the tool or directly compare to alternatives like 'resolve_citation' or 'find_citing'.

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