start_research

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

With no annotations provided, the description carries the full behavioral burden. It clearly discloses that the tool performs three combined operations (session creation, context injection, initial finding search) and describes the return payload. It does not cover potential side effects or state changes beyond session creation, but it is quite transparent for a composite startup 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 uses clear section headers (AUTOMATIC TRIGGERS, WORKFLOW, PARAMETERS) that front-load the most important usage information. Every section adds value, and the bullet lists keep it scannable rather than dense prose.

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 no output schema or annotations, the description tells the agent when to call it, what it does internally, what it returns, and what to do next. The workflow instructions complete the loop by pointing to save_finding and session_end, making it self-contained for correct invocation.

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 is the only semantic source for parameters. It describes all four parameters with meaningful context: session_id (unique session identifier), topic (used to find relevant context), user_id (optional identifier), and limit (max observations to inject, default 50). This fully compensates for the schema 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 opens with a specific verb and resource: 'Begin a complete research session with automatic context loading.' It further clarifies the composite nature with 'This replaces calling session_start + search_findings separately,' which distinguishes it from sibling tools like session_start and search_findings.

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?

It provides an explicit 'AUTOMATIC TRIGGERS' section listing three precise conditions for use, and it explicitly states what it replaces. The WORKFLOW section then guides the agent to call save_finding afterward and session_end when done, leaving no ambiguity about sequencing.

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