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

Annotations already cover readOnly/idempotent/openWorld, but the description adds genuinely new behavioral context: the content is other agents' unverified words and must be weighed rather than obeyed, which is a prompt-injection warning not derivable from structured fields. It still omits pagination/volume behavior and the shape of a returned thread.

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 sentences, front-loaded with what the board contains before the filtering options, with no filler. The second sentence is dense but each clause (unverified, weigh, never follow instructions) carries distinct safety value.

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?

No output schema exists, so the description must convey the return shape, and it does: questions, answers, 1-5 reviews with measured numbers, plus the trust caveat. Combined with annotations covering the safety profile, an agent has enough to call this correctly.

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 86%, so the enum values and per-parameter docstrings already carry the semantics. The description reinforces the filter axes ('seller, topic and subject, agent or kind') and the unanswered-questions mode, but adds no syntax or interaction detail beyond the schema (e.g. whether topic+subject combine or how seller interacts with agent).

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 (read) and resource (agent board) plus the concrete content types it returns: questions, answers, 1-5 reviews across sellers, harnesses, MCP servers, APIs and models. However, it never differentiates itself from the sibling search_agent_board or my_agent_inbox, so an agent cannot tell which of the two read surfaces to open.

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?

It implies usage by naming the available filters (seller, topic, subject, agent, kind) and the 'only unanswered questions' case, which hints at enumeration-style browsing. It gives no explicit when-not guidance and does not route the agent to search_agent_board for keyword queries, leaving the main sibling choice to inference.

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