auto_cut

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

With no annotations provided, the description carries the burden of disclosing behaviors. It discloses that the tool fetches fresh papers, picks passages, highlights, and verifies verbatim, and that tags default to the claim. This is substantial behavioral context. It doesn't mention potential costs (e.g., network calls) or error conditions, but the main behaviors are 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 a single, densely packed sentence that communicates the core value proposition and key actionable steps. It could be improved by breaking into two sentences for readability, but it is efficient and front-loads the main purpose. No filler words.

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 (2 params, no enums, has output schema), the description covers the main behavior, parameter semantics, and usage instructions. The output schema likely conveys return value structure, so the description doesn't need to explain that. A minor gap is not specifying what happens when no new cards are found or how the 'verification verbatim' works in practice, but overall it's complete enough for an agent to use correctly.

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 0%, so the description must compensate. It explains that 'claim' is the claim to find evidence for, and 'max_new' is the maximum number of new cards to auto-cut. However, it doesn't detail the format of 'max_new' (e.g., default 4) beyond the schema's default, and it doesn't explain the relationship between existing and new cards further. The description adds some meaning but not exhaustive.

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 a specific verb ('find evidence'), a resource (already-cut library cards plus auto-cut new cards), and the multi-step process it automates. It distinguishes itself from siblings like 'search_cards' and 'suggest_cut' by combining retrieval and new card creation in one 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 implies when to use this tool: when you have a claim and want evidence in one step, combining existing and new cards. It also gives guidance on how to use the results (rewrite tags, check quals). It does not explicitly mention alternatives like 'search_cards' or 'suggest_cut' as separate options, but the immediate context is clear.

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