interpret

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

With no annotations, the description carries the full burden of behavioral disclosure. It does reveal the two-step process (parsing and Claude reading), the caching behavior, and the cost optimization ('free input tokens'). However, it does not explicitly state that the tool is read-only (implied but not stated), nor does it mention error handling, rate limits, or potential side effects. For a tool that presumably only reads and answers, this is adequate but not fully transparent.

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 and well-structured. The first sentence states the core purpose, the second gives usage examples, and the third explains the workflow and caching. Every sentence earns its place with no fluff. The information is front-loaded with the core functionality.

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, 100% schema coverage, and the presence of an output schema, the description is quite complete. It explains the internal workflow, caching benefits, and the type of requests it handles. The output schema presumably covers return values, so the description need not repeat those. It does not detail supported source formats or error cases, but these are likely covered by the backend parameter and output schema. Slight gap on edge cases, but overall adequate.

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 description coverage is 100%, so the baseline is 3. The description does not add any parameter-specific information beyond what the schema already provides. While the examples hint at 'source' and 'instruction', the schema itself already describes each parameter (model, source, backend, max_tokens, instruction) clearly. The description adds no additional semantic depth.

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's function: 'Parse the document, then ask Claude over the parsed markdown.' It specifies the verb (parse and ask) and the resource (document), and the examples ('summarize this PDF', etc.) solidify the purpose. It implicitly distinguishes itself from parsing-only siblings like 'parse' and 'parse_url' by adding the Claude interrogation step.

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 directly tells the agent when to use the tool with 'Use this for... style requests' and provides concrete examples. It also explains the internal workflow (router parses, then Claude reads) and caching benefits. However, it does not explicitly state when NOT to use it or mention alternative tools (e.g., 'if you only need the parsed text, use parse'), leaving some inference to the agent.

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