conversations_search_messages

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

With readOnlyHint=true already covering the safety profile, the description goes beyond annotations by disclosing search operator syntax, the special message-URL behavior, the accepted date formats and their during-vs-other semantics, the limit range, and notably the cursor rule that filters supplied with a cursor are ignored. That cursor caveat is genuinely non-obvious behavior an agent would otherwise get wrong.

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?

Dense, telegraphic and front-loaded: the core verb comes first, then input syntax, then paging rules. Every clause carries information, though the date-format sentence is cramped and requires careful parsing.

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 tool with zero schema documentation, the description covers most of what is needed to call it correctly, and the existence of an output schema means return values need not be described. The gaps are the two unexplained filter parameters and the absence of sibling routing guidance.

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 12 parameters, so the description carries the full burden. It supplies value formats for search_query, user filters (ID, @handle, name), channel filters (ID or #name), the date filter family, limit, and cursor. It does not explain filter_threads_only or filter_in_im_or_mpim, leaving two parameters undocumented anywhere.

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 messages') and even names the output form (CSV). It does not distinguish itself from close siblings like conversations_history or conversations_replies, so an agent gets no explicit routing signal, but the purpose itself is unambiguous.

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 implicitly tells the agent how to use the tool by explaining that search_query takes Slack modifiers or a full message URL (which then returns that single message), which is a quasi-usage signal. However, there is no explicit when-to-use / when-not-to-use guidance and no mention of the sibling tools that overlap (conversations_history, conversations_replies).

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