find_parallels

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

The description discloses a key limitation: 'a match does not establish identity, authorship, date, or a physical join.' It also notes that the public API currently supports only chunk matching. These are useful behavioral caveats, but no other behavior (e.g., error handling, side effects, or return format) is described.

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, with two sentences that convey the tool's purpose and a key caveat. There is no verbosity or irrelevant content. However, the brevity means it lacks structure for more complex aspects, but it is well-organized for what it covers.

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 far from complete given the complexity of the schema. It does not explain what the input should contain, how filters work, what the output looks like, or any constraints. Without this, an agent cannot correctly invoke the tool beyond a basic text query, making it inadequately contextualized.

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 description provides no explanation of any parameters. The schema defines a nested 'input' object with numerous fields (mode, text, filters, chunk_size, boundary_mode, etc.), but none are interpreted or described. Since schema coverage is 0% and the description fails to compensate, this dimension scores poorly.

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 core function ('Find candidate textual chunk parallels') and differentiates it from sibling tools like search_manuscripts and browse_page by focusing on finding parallels rather than searching or browsing. The phrase 'chunk matching only' adds specificity, though the exact meaning of 'parallels' could be clearer.

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?

No guidance is provided on when to use this tool versus the sibling tools. The description does not mention any conditions or scenarios that would make this tool the preferred choice, nor does it contrast it with alternatives.

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