create_poster

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 behaviors: validation of PosterBrief, returning missing questions, archiving, and not guessing sensitive fields like eventName, VAT policy, etc. It also states a prerequisite condition. However, it does not specify what happens on success (e.g., returns created poster) or failure modes beyond missing questions, nor does it mention side effects like overwriting existing posters. The disclosed behaviors are accurate and useful, warranting a 4.

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 concise, with two sentences. The first sentence states the tool's purpose and precondition, and the second explains the validation behavior. It is front-loaded, imparts critical constraints, and contains no filler or redundancy. Every word contributes meaning.

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 tool is complex (15 params, nested objects, enums, no output schema). The description clearly conveys the validation-first approach and the requirement to know operating and price-display rules. It does not mention the return format (e.g., whether it returns the created poster or just success), nor does it clarify how the content object should be structured beyond the schema. It covers the 'when' and 'why' but lacks details on the 'what happens after' and full parameter semantics, leaving gaps for an agent to invoke it 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?

Schema description coverage is 0%, so the description must compensate. It explicitly names several parameters (eventName, VAT policy, table preference, table style, program separation) and indicates they are conditionally required and must not be guessed. However, it does not explain the meaning or usage of many other parameters (mood, tags, year, month, notes, style, theme, render, status, etc.), leaving the agent to rely solely on the raw schema. The description adds value for the validation-related parameters but is insufficient for full parameter understanding.

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: 'Create and archive a new HTML/CSS poster'. It specifies a concrete action (create + archive) on a specific resource (poster), and distinguishes it from siblings like render_poster or update_poster by focusing on creation and validation. The mention of 'only after required operating and price-display rules are known' adds specific scope, differentiating it from a generic create tool.

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 explicit preconditions ('only after required operating and price-display rules are known') and explains that it will 'return missing questions instead of guessing', clarifying when to use it (when brief is incomplete but validation is needed). It does not explicitly name alternative tools (e.g., render_poster for rendering), but the context signals and unique validation behavior imply the appropriate use case. This is clear guidance but lacks explicit exclusions.

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