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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the output is a PDF, details the return as a 'download link that expires within ~48 hours,' and explicitly says 'Nothing you submit is stored.' It also defines the division of labor between the agent (judgment) and the tool (format). This is substantive, non-redundant transparency that goes well beyond the schema.

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 consists of three sentences, each adding unique value: the core purpose and structure, the expectation of user judgment, and the transient/storage behavior. There is no repetition of schema details and no filler. The most critical information (what it generates) is front-loaded.

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?

For a tool with 16 parameters, no output schema, and no annotations, this description is appropriately complete. It covers what the tool produces, the sections it contains, how it behaves (link expiry, no storage), and the user's responsibility. It does not mention error conditions, prerequisites, or alternative tools, but those are not critical for a PDF generator. The schema covers the parameter details, so the description fills behavioral gaps effectively.

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 covers 63% of parameters, so the description does not need to fully enumerate them, but it compensates by mapping the logical document structure (header, meta grid, subject, description, proposed solution, attachments) to input fields. The guidance about 'exact drawing references' and 'a proposed path forward' clarifies the intended semantics for drawing_refs, proposed_solution, and attachments. However, some schema-uncovered parameters (e.g., response_needed_by, company_location) are not addressed, leaving a minor 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 'Generate a formal Request for Information PDF from structured fields,' which is a specific verb+resource combination. It further clarifies scope by listing the included sections (header, meta grid, subject, description, proposed solution, attachments, response block) and explicitly differentiates the tool's role as a formatter, not a content creator. Although it does not name sibling tools, 'RFI' in both name and description is unmistakably distinct from NCR/RFQ generators.

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 gives clear usage context: 'You do the judgement (one issue per RFI, exact drawing references, a proposed path forward); the tool guarantees the format.' This implies the appropriate workflow—prepare content, let the tool handle formatting—but does not explicitly state when to use this tool versus alternatives (e.g., steel_ncr_generate or steel_rfq_generate). No exclusions or when-not conditions are provided, so it stops short of a 5.

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