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 results are 'when available' for borrow fee and AI-generated research, setting accurate expectations. It also mentions the paid HTTP endpoints as an alternative access method. It does not cover error handling or rate limits, but for a read tool the key behaviors around data availability and access are addressed.

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, both dense with relevant information. The first sentence lists the comprehensive data set, the second gives usage constraints and alternative endpoints. While it is a wall of text without bullet points, it is still concise and every clause adds value.

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 tool's complexity (a full IPO profile with many data fields) and the absence of an output schema, the description is remarkably complete. It lists specific content areas, notes optional data via 'when available', specifies the input constraint, and even provides HTTP endpoint alternatives. This gives an agent enough context to understand the tool's capabilities and limitations.

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 three parameters with 0% description coverage, so the description must compensate. It does by stating that exactly one of companyId, symbol, or cik should be provided, clarifying they are mutually exclusive identifiers. It also maps symbol and id to alternative HTTP endpoints, giving extra context. However, it does not elaborate on the meaning or format of each identifier, leaving some ambiguity.

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 verb 'Retrieve' and the resource 'complete IPO company profile', enumerating specific content areas (deal terms, pricing range, SEC registration, etc.). This distinguishes it from sibling tools like get_company_metrics and get_ipo_sentiment, which focus on narrower data.

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 on what the tool returns, allowing an agent to infer it for full-profile needs. It explicitly instructs 'Provide exactly one of companyId, symbol, or cik,' which is an important usage rule. However, it does not explicitly state when not to use this tool or name alternatives beyond implying their existence through sibling names.

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