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

With no annotations, the description carries the full burden and does so well: it discloses that every returned post is billed to the operator, that own posts are always excluded, the 10..300 cap on max_posts, the exact filters safe_defaults appends, and that nothing is posted/liked/replied to. This is unusually rich behavioral disclosure for a mutation-adjacent tool.

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?

Front-loads the purpose and the critical either/or parameter rule, and every sentence carries information (billing, filters, incremental reads). It is dense with parentheticals and the weights key enumeration is long, but nothing is truly wasted.

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?

Covers purpose, parameter routing, billing, filters, and side-effect safety, which is most of what an agent needs; the return-key list is partly redundant given an output schema exists. Missing auth/credential expectations and the dpop_token parameter keep it short of full completeness.

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 only 14% (npub alone), so the description must compensate, and it does for six of seven params: query_id vs query semantics, safe_defaults' appended filters, max_posts range, and the full weights key list. It leaves dpop_token entirely undocumented in both schema and description, which is the remaining gap.

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 X's last 7 days for people asking something you could answer'), plus the scoring and storage side effects, and names the sibling it feeds ('list_conversations') and the source of saved queries ('save_conversation_query'). An agent can distinguish this from list_conversations and save_conversation_query without opening a schema.

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 an explicit routing rule: 'Pass exactly one of query_id (a saved query from save_conversation_query) or query (an ad-hoc X search clause)', and explains the incremental behavior of a re-run saved query. This tells the agent which parameter path to take and when each applies.

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