compose_special

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

With no annotations, the description carries the full burden. It discloses that source books and the question bank are not modified, explains the effect of missing secHint (creates new section), and specifies error conditions for empty picks or not logged in. It does not cover authentication requirements or rate limits, but these are typical and somewhat assumed.

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 well-structured: a one-sentence summary, then detailed explanation of the special's structure, parameter descriptions, and return values. It is slightly verbose but each sentence adds value. Could be tightened slightly, but overall efficient.

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 complexity (4 parameters, picks as array of objects) and presence of output schema (described in text), the description covers key aspects: creation process, parameter details, return values including skipped items. It lacks mention of prerequisites like login status beyond the error case, but is otherwise comprehensive.

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 adds significant meaning beyond the input schema, which has 0% coverage. It explains the special naming constraint (clean knowledge name, no internal terms), details the picks structure with subfields (questionId/nodeId, secHint, overrideJson), and notes optional grade/subject_id. This compensates fully for the lack of schema descriptions.

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 defines the tool's purpose: building a 'special' document by selecting materials across multiple books and batch-picking questions into blocks. It specifies the structure (block → tier → question) and explicitly distinguishes from papers, which is a key sibling differentiator.

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 explains that the tool is used for creating specials (non-papers) with cross-book selection, and notes that picking occurs within a block framework. It does not explicitly list when not to use it, but the context (e.g., 'non-paper') and sibling tools (like compose_paper) provide implicit guidance.

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