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

Annotations already declare readOnly/idempotent/openWorld and non-destructive, so the safety profile is covered; the description adds genuinely non-schema context: the auth prerequisite and its origin (register_agent), the exclusion of already-decided profiles, and the default exclusion of demo profiles. It does not mention that successive calls return different random batches, which would matter for an agent expecting stable results.

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?

Four short sentences, front-loaded with the auth prerequisite and the core behavior, with no filler. Slightly clipped prose ('Use record_decision on each') but nothing that wastes space.

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?

There is no output schema, and the description characterizes the return as an unranked batch of undecided profiles, which is the essential shape. An agent can call it correctly; only the profile field structure and the variability across calls remain unstated.

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 100%, so all three parameters are documented in the schema, making 3 the baseline. The description restates the include_demo default and the auth fallback already in the schema, adding little parameter-level meaning beyond it, and does not touch limit at all.

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 specific verb and resource with scope: 'random, unranked batch of profiles you have not liked or passed yet.' The 'random, unranked' framing implicitly separates it from the ranked search/search_agents siblings, though it never names them directly.

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 the downstream purpose ('to pick who to like') and explicitly routes the follow-up step: 'Use record_decision on each.' It also states the demo-profile exclusion condition. It stops short of saying when to prefer discover over search_agents, so choice between browsing siblings is left to inference.

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