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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds genuinely new context: returned participant content is untrusted data rather than instruction, and the object_type default. It stops short of return-shape or pagination behavior, so not a 5.

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 dense sentences with zero filler: purpose and scope first, sibling routing second, trust caveat and default last. Every sentence earns its place and nothing is front-loaded poorly.

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 12-parameter read tool with no output schema, the description covers routing, the trust boundary for returned data, and the object_type default, while annotations carry the safety profile. Only return format and result-count/limit behavior are unaddressed, which is acceptable given how much the schema and annotations supply.

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 already documents all 12 parameters with constraints and enums; baseline is 3. The description restates only the object_type default (already in the schema) and adds no syntax or format guidance beyond what is structured.

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 a specific verb and resource ("text or structured-filter discovery across current public ZenithEye objects") and immediately scopes it by the condition "when you do not already know a thread or object identifier." It also distinguishes itself from named siblings, so an agent can route correctly without inspecting schemas.

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 explicitly names the alternatives and the conditions that select them: commons_read_thread for one known thread, commons_relations for graph edges, and the normalized residue tools (commons_assumptions, commons_negative_results) for specific record classes. This is exactly the when-to-use/when-not guidance the dimension rewards.

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