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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and a closed-world scope, so the safety profile is fully covered and the description adds nothing new. Critically, it does not disclose the one behavior that matters here: whether polling consumes/drains messages or leaves them in place for repeat reads.

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 words, front-loaded with the scope tag and the operation, with no filler. Given the empty schema, brevity is defensible, though it is arguably too little to be useful rather than tight.

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 and no annotations describing payload, the description should explain what a poll returns (message list shape, ordering, empty-state) and whether messages are acknowledged. None of that is present, so an agent knows only the name of the operation, not what it will get back.

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?

The tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The schema fully covers the (empty) input surface.

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 gives a verb+resource ('Poll swarm inbox') and the '[agents]' tag hints at agent-scoped messages, so the general domain is clear. But it never says what an 'inbox' holds (messages, tasks, relays?) or how it relates to siblings like swarm_relay, so an agent cannot sharply distinguish it from adjacent swarm tools.

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?

There is no statement of when to call this versus alternatives such as swarm_relay, nor any note about polling cadence, frequency limits, or whether it should be called repeatedly. Usage is only weakly implied by the word 'Poll'.

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