search_problems_boj

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

Discloses a critical output behavior: results are returned as a markdown table with mandatory links to BOJ problem pages that must be preserved. Since no annotations exist, this is valuable beyond structured fields. It does not cover all behaviors (e.g., pagination), but the key user-facing behavior is 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 moderately concise and structured, with the main sentence, link warning, and example all earning their place. However, the final line about platform unspecified is confusing and redundant for a BOJ-specific tool, adding noise and reducing clarity.

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 covers purpose, filter dimensions, output format, and examples, which is adequate for basic use. Given 7 optional parameters and no output schema, it could benefit from clarifying tag combination semantics (AND/OR) or result limits. The confusing platform line also detracts from completeness.

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 input schema already describes all 7 parameters with detailed descriptions and 100% coverage. The description summarizes the main filter dimensions and gives an example, but adds little beyond the schema. The baseline of 3 is appropriate.

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 searches BOJ problems with filters for keyword, difficulty level, and algorithm tags. It distinguishes from sibling tools by scope (get_problem for single problems, search_tags for tags) though not explicitly; the final line about unspecified platform introduces slight ambiguity.

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?

Concrete examples ('Gold tier DP problem search', 'Silver or lower greedy problem search') illustrate when to use the tool. The platform reminder, though oddly placed, suggests clarifying the platform when unspecified, which is relevant given the sibling search_problems_programmers tool. No explicit exclusions are provided, but the context is adequate.

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