AxKnowledgeBase_get_knowledge_base_paper_markdown

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

With no annotations provided, the description carries the behavioral burden. It discloses the output format (markdown in reading order) and the sections included, which is useful. However, it does not mention any error cases (e.g., paper not found), performance expectations, or whether it is a read-only operation. Given it's a simple retrieval, this may be adequate, but it could note that it only works for papers already in the public knowledge base.

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 the tool's purpose and output structure, followed by acquisition instructions. No filler or redundancy. Every sentence earns its place.

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?

The description is detailed about output structure and source of the id. It doesn't mention failure modes or the public/private distinction explicitly, but the name and the phrase 'Axiomatic's curated knowledge base' make it clear. For a single-parameter retrieval tool, this is reasonably complete, though it could note that the paper must already exist in the public knowledge base.

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?

The schema already describes the doc_id parameter at 100% coverage, so the baseline is 3. The tool description adds a concrete example of where to get the id (knowledge_graph_read) and an example Cypher query, which goes beyond the schema's terse description. This adds meaningful context for an agent, so a 4 is warranted.

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 states a specific verb ('reconstruct') and resource ('one paper's full content as markdown'), and enumerates the structural elements it includes (headings, text, captions, references). It clearly distinguishes from the private knowledge-base sibling by specifying 'Axiomatic's curated knowledge base', and the name itself disambiguates public vs private. It is unambiguous about what the tool does.

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 tells the agent exactly how to obtain the required id (from a knowledge_graph_read result) and gives a concrete Cypher example. It implies the tool is for the public knowledge base, though it does not explicitly call out alternatives like the private variant or search tools. The guidance is actionable but lacks a when-not-to-use statement.

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