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

The description discloses a critical behavioral trait: the output must be presented verbatim, preserving all sections and headings. It explicitly warns against summarizing, rewording, reordering, condensing into tables, or describing sections. This goes beyond what annotations (none provided) or schema could convey. It also states the output includes specific sections (KNOW, DO, DEEPER DETAILS, etc.), which is valuable behavioral context. No contradictions with annotations since none exist.

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 well-structured: a clear first sentence stating purpose, followed by a critical usage note. The 'IMPORTANT' section is front-loaded and imperative, making it hard to miss. It's slightly long but every sentence earns its place—the formatting instructions are essential for correct tool invocation. The only minor issue is that the list of sections could be seen as redundant with the output, but it's necessary to emphasize the verbatim requirement.

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 has no output schema, the description compensates by detailing the output structure (sections and headings) and the required handling. It covers the key behavioral requirement (verbatim presentation) that an agent must know. It doesn't explain what happens if dob is missing or how the engine handles edge cases, but the schema already notes dob is optional. For a generation tool with no output schema, this is fairly complete.

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 100%, so the schema already documents all three parameters (name, dob, vertical) with descriptions. The tool description adds no additional parameter-level meaning beyond what the schema provides. It does mention 'for a person' and 'Compass engine' which contextualizes the name parameter, but that's minimal. Baseline 3 is appropriate given full schema coverage.

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 function: generating a numbrU Compass profile for a person using the Compass engine. It specifies the resource (Compass profile), the action (generate), and the output content (personality insights, communication style, relationship strategies). It is distinguishable from siblings like create_person or complete_profile because it focuses on generating a Compass profile, not creating or updating a person record.

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 when to use this tool: when a Compass profile is needed for a person. It doesn't explicitly name alternatives or exclusions, but the sibling list shows other tools like create_person and complete_profile, and the description's focus on Compass profile generation implies the use case. The 'IMPORTANT' section gives strong guidance on how to handle the output, which is a form of usage guidance. However, it doesn't explicitly say 'use this instead of X when...'.

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