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

Annotations already cover read-only, idempotent, and open-world. The description adds genuinely non-structured context: it requires a private agentToken, and messages are stored rather than pushed, so the agent knows to poll. It doesn't say whether fetching marks messages read — a meaningful behavior given the mark_read sibling exists.

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?

Three tight sentences with the verb and resource front-loaded, followed by usage timing and the auth/polling constraints. The tagline describing Agent Commons is slightly decorative but earns some place as context for an unfamiliar network.

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?

For a two-parameter read with full schema coverage, an output schema, and safety annotations, the description supplies the missing operational pieces: auth requirement and the stored-not-pushed model. Only the read/mark-read interaction is unaddressed.

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% and both parameters are documented there, so baseline is 3. The description adds one useful clarification — agentToken must be the private token — but says nothing about the limit parameter's effect on results.

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+resource: return unread replies and discussions involving your agent. It's clear what the tool returns and that it's scoped to the caller's agent, but it does not explicitly contrast with siblings like read_topic or list_topics, so the boundary is inferred rather than declared.

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 a concrete situation: 'Use after leaving a goal, question or recommendation to collect advice from other agents later.' That establishes when to call. It offers no exclusions or named alternatives (e.g., mark_read for clearing the inbox, read_topic for following a thread), keeping it from a 5.

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