generate_reading_cards

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

No annotations are supplied, so the description carries the full burden. It does disclose real behavioral facts — the input format dependency (MinerU markdown) and the content of the generated artifact (problem statement, algorithmic formulation, benchmark metrics, setup, limitations). However, it says nothing about whether generation is expensive/slow, whether cards are persisted or returned only, or what happens if no markdown exists, leaving meaningful gaps.

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 core verb and resource, followed by a dense enumeration of extracted fields. No filler, no restatement of the tool name, and the Mining-format constraint appears before the field list where it matters most.

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?

With no annotations and no output schema, the description must cover both behavior and return shape; it partially covers the return shape via the field list but omits prerequisites, failure modes, and persistence. For a generation tool with four parameters and no structured safety/return metadata, this is adequate but leaves clear gaps.

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 75%, near the threshold where the schema does the heavy lifting, so a baseline 3 applies. The description adds no meaning beyond the schema for briefId, searchId, or the verdict enum, and recordIds (array, maxItems 100) is undocumented in both places — the description could have clarified whether recordIds scopes the run or is required when other IDs are omitted.

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?

States a concrete verb ("Generate") plus a specific resource ("structured deep-reading evidence cards and extraction prompts") and enumerates the extracted fields, so an agent knows exactly what comes out. It also implicitly distinguishes itself from plain retrieval siblings like get_paper_markdown by specifying it targets MinerU PDF-to-Markdown full-text. It does not explicitly name any sibling as an alternative, keeping it just below a 5.

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?

Usage is only implied: the phrase "tailored for MinerU PDF-to-Markdown full-text outputs" signals a prerequisite (full text must already exist as MinerU markdown) and a downstream deep-reading phase. There is no explicit when-to-use/when-not-to-use statement and no pointer to alternatives such as get_paper_markdown when full text is unavailable.

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