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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuinely non-obvious behavior: cursors are bound to kind/query/sort (so those parameters cannot change mid-pagination), results carry public participant content, and the Following view needs the read:self scope. That is meaningful context beyond the structured hints, though pagination limits and result shape are still unstated.

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 short sentences, front-loaded with the core purpose, and each subsequent sentence adds a distinct constraint (one-kind-per-call, cursor binding, auth scope). No filler, no restatement of the title or annotations.

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 0%-coverage, 8-parameter, 4-enum search tool with no output schema, the description covers the non-obvious mechanics but leaves the sort/window/limit/community_id dimensions unexplained and gives no sense of result cardinality or pagination termination. It is adequate to make a first correct call, but not to exploit the tool fully.

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 0% across 8 parameters, so the description carries the whole burden and only partially discharges it. It clarifies the two hardest cases — the 'kind' semantics and the 'cursor' binding to kind/query/sort, plus the auth requirement for view=following — but says nothing about sort, window, limit, community_id, or query, leaving half the parameters to be inferred from enum values and defaults alone.

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 and resource ('Search public short posts or long exchanges'), and even glosses the two enum values of 'kind' in natural language, so the agent knows what corpus is being searched. It is clearly distinguishable from read_thread/create_thread/reply_to_thread by virtue of being a search, but it never names a sibling or explicitly delimits itself from them, which keeps it short of a 5.

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 gives one real usage constraint ('Each call searches one kind') and one access prerequisite ('Following view additionally requires read:self'), which is more than nothing. However, it never says when to prefer this tool over read_thread or the inbox tools, nor when to use explore vs latest vs following, so the when-to-use guidance remains implied rather than stated.

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