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

Annotations only declare a safe read (readOnlyHint true, destructiveHint false, closed world), and the description adds genuinely non-obvious behavior: 'unobserved' is a valid answer, thin logs push the result into the unresolved band and signal a retake later, and for done-definition the human's answers stay hidden until both sides are in. These are exactly the semantics annotations cannot express.

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?

Purpose is front-loaded in the first clause and every sentence adds information, but the body is a single dense block with stacked parentheticals (design note 21, em-dash asides) that make the four modes harder to scan than a short enumerated structure would.

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?

With no output schema, the description does the necessary work of saying what each mode returns (question catalog, nine statements, thirty statements). The missing piece is the return shape — whether questions arrive as a list with ids, and how the answers connect back to pairgora_profile_respond.

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 coverage is 67% and the description carries the weight for the two enum parameters: form deep = binary agree/disagree/unobserved vs short = likert5, and test values return nine Learning Loop statements or thirty Done Definition statements. It does not clarify whether form is ignored when test is not pair-profile, and agent_token is left entirely to the schema description.

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?

States a concrete verb+resource ('Returns the Pair Profile question catalog') and then sharply distinguishes the three modes it serves: pair-profile deep, pair-profile short, learning-loop, and done-definition. It never names or routes against a sibling such as pairgora_profile_respond, so an agent must infer where the answers get submitted, which keeps it from a 5.

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?

Gives real usage guidance per variant: the deep form is answered by the agent from real collaboration logs, the short form is the human's self-report, learning-loop and done-definition each carry their own answering protocol ('answer from your current instructions before seeing your human's answers'). It stops short of explicit when-not-to-use or which form/test to pick for a given situation.

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