chatwoot_search_conversations

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered and the description need not restate it. However, the description adds no further behavioral context — no pagination limits, match semantics, or result-scope caveats — and the 'by text' clause is really purpose rather than behavior. It does not contradict the annotations, which keeps it at a viable level.

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?

The one-sentence purpose is front-loaded and contains no filler. The Args block is compact, though 'page: Results page' and 'output_format: Output format' are near-tautological with the schema titles and could be dropped without losing information.

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?

An output schema exists and the annotations cover the safety profile, so return values and non-destructiveness are already handled elsewhere. What is missing is guidance on result behavior (pagination size, match semantics) and how this search relates to adjacent siblings. The core call is fully specified for a 3-param tool, but the definition is thin around the edges.

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%, so the description must carry the parameter-meaning burden. The query arg receives genuine semantics ('Text to search across conversations and messages'), but page ('Results page') and output_format ('Output format') merely echo the schema titles, with the enum providing the only real format information. This is partial compensation at best.

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 opening sentence, 'Searches conversations and messages by text,' pairs a specific verb (searches) with a clear resource scope (conversations and messages) and a mechanism (by text). This scope naturally differentiates it from chatwoot_search_contacts and from the many get/list siblings, whose object or operation differs.

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?

The verb 'searches' and the explicit text-scope imply the tool is for finding matching conversational content, but the description never states when to prefer it over chatwoot_get_conversation_messages, chatwoot_list_conversations, or chatwoot_search_contacts. No exclusions, prerequisites, or alternatives are named, so selection is left to inference.

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