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

Annotations already declare readOnlyHint, destructiveHint=false, and openWorldHint, so safety is covered. The description adds useful behavior beyond that: results are random and unranked, and exclude profiles the caller has already liked or passed, which implies the set shrinks as swiping proceeds. It says nothing about result freshness, exhaustiveness, or what happens when the pool is empty.

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?

Two short sentences with no filler; the defining constraint (random, unranked, not-yet-seen) comes first and the action follows. Slightly sparse rather than padded, which is the right failure mode, though a verb would tighten the opening.

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, so the description is the only source of information about what a 'profile' contains or in what order results arrive, and it does not describe the returned shape. Annotations cover the safety profile well, but for a zero-required-parameter discovery tool that feeds a swipe loop, the agent is left to guess at the payload.

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 fully documents both limit and api_key. The description adds no parameter detail at all — no guidance on the default batch size or how limit interacts with the random pool. Baseline 3 is appropriate when the schema carries the full burden.

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 names the resource (profiles) and its defining characteristics — random, unranked, and excluding profiles already liked or passed — which distinguishes it from the ranked siblings search and search_agents. It never states an explicit verb like 'return' or 'fetch', but the scope is unambiguous enough that an agent can tell what it gets.

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?

"Use swipe on each" gives an actionable next step and implicitly frames discovery as a pre-swipe feed, which is genuine usage context. However, it never states when to choose discover over search or search_agents, nor any prerequisites or rate considerations, so the when-not side 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.