compose_question

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

With no annotations provided, the description carries the full burden. It discloses key behavioral traits: how parts are placed ('placing each where the retrieval measurements say it belongs'), which parts are indexed versus not, and the return value ('the question object plus what is still missing from it'). This goes beyond a simple action statement, though it omits details on side effects or permissions, which are less critical for a composition tool.

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 two sentences, front-loaded with the main action, and each sentence earns its place. It includes essential behavioral and return information without redundancy. It is appropriately sized for the tool's complexity.

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?

Despite having an output schema, the tool is moderately complex with 11 parameters, many of which are unexplained. The description focuses on the four main parts and the compositional logic, but omits guidance on the other parameters, prerequisites, or error conditions. It leaves significant gaps for an agent to invoke the tool 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?

The schema has 11 parameters and 0% schema description coverage, so the description must compensate by explaining parameter meanings. It only vaguely references 'four parts' without mapping them to specific fields. For instance, it never mentions parameters like 'people', 'observation', or 'priority'. The description provides minimal semantic value beyond the schema.

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 states a specific action: 'Assemble one pack question from the four parts', clearly identifying the resource (pack question) and the process (assembling based on retrieval measurements). It distinguishes itself from sibling tools like parse_meeting_notes or validate_pack by focusing on composition rather than parsing or validation.

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 provides clear context for when to use the tool: when you have the four parts and need to assemble a question according to retrieval measurements. It implies the prerequisite of having those parts, but does not explicitly name alternatives or exclusions. This meets the 'clear context, no exclusions' level.

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