Prepare research request

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

Annotations readOnlyHint=true and openWorldHint=false are supplemented by detailed behavioral disclosure: deterministic assembly, no model calls, return structure (questions, sources, spec, saveInstruction, model suggestion), and skip behavior. The description adds rich context about what the tool produces and how it interacts with other tools (e.g., add_kb_doc), far beyond what annotations alone convey.

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 fairly concise given the complexity, front-loading the action and outcome. However, it includes implementation references (FBMCPF-263, FBMCPF-264) that may be noise for an agent. The structure clearly lists return components, but the inclusion of ticket IDs for internal tracking reduces readability. Still, it conveys essential information efficiently.

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 comprehensive: it covers all return fields (questions, sources, spec, saveInstruction, model), conditional behavior (skip on off, forced on), and config/label interaction. Without an output schema, the description fully explains the expected output. This completeness, combined with annotations, makes the tool well-specified for an agent.

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 description coverage is 0%, so the description must explain the two parameters (ticket and project). Although 'ticket' is implied in the purpose ('for a ticket'), the 'project' parameter is not described at all. No details are given about expected format, values, or constraints. The description focuses on behavior but neglects input semantics, leaving a significant gap.

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 purpose: 'deterministically assemble a research REQUEST packet for a ticket BEFORE implementation'. It specifies the exact resource (research request for a ticket) and action (assemble), and the mention of 'no model calls' distinguishes it from generative tools. Among siblings like search_kb or append_research, this tool's unique role is well-defined.

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 usage context: use it before implementation, skip when research is off, and force with labels. It explains return behavior for both on and off states. However, it does not explicitly mention alternative tools or when not to use it, which would be helpful for an agent to decide between this and other research-related tools like search_kb.

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